xclele/yolov10
1
0
Fork 0
mirror of https://github.com/THU-MIG/yolov10.git synced 2025-05-23 05:24:22 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

ultralytics 8.1.0 YOLOv8 Oriented Bounding Box (OBB) release (#7463)

Browse Source 
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: UltralyticsAssistant <web@ultralytics.com>
Co-authored-by: Laughing <61612323+Laughing-q@users.noreply.github.com>
Co-authored-by: Yakuho <Yakuho@foxmail.com>
Co-authored-by: Oran <75175510+Acenath@users.noreply.github.com>
This commit is contained in:
Glenn Jocher 2024-01-10 10:57:40 +01:00 committed by GitHub
parent 54e61963c8
commit 808984c6cf
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
95 changed files with 787 additions and 752 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

62
README.md
View File

@ -124,11 +124,11 @@ See [Detection Docs](https://docs.ultralytics.com/tasks/detect/) for usage examp
| Model | size<br><sup>(pixels) | mAP<sup>val<br>50-95 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) | | Model | size<br><sup>(pixels) | mAP<sup>val<br>50-95 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) |
| ------------------------------------------------------------------------------------ | --------------------- | -------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- | | ------------------------------------------------------------------------------------ | --------------------- | -------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 | | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 |
| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 | | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 |
| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 | | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 |
| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 | | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 |
| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 | | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 |
- **mAP<sup>val</sup>** values are for single-model single-scale on [COCO val2017](http://cocodataset.org) dataset. <br>Reproduce by `yolo val detect data=coco.yaml device=0` - **mAP<sup>val</sup>** values are for single-model single-scale on [COCO val2017](http://cocodataset.org) dataset. <br>Reproduce by `yolo val detect data=coco.yaml device=0`
- **Speed** averaged over COCO val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val detect data=coco.yaml batch=1 device=0|cpu` - **Speed** averaged over COCO val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val detect data=coco.yaml batch=1 device=0|cpu`
@ -141,11 +141,11 @@ See [Detection Docs](https://docs.ultralytics.com/tasks/detect/) for usage examp
| Model | size<br><sup>(pixels) | mAP<sup>val<br>50-95 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) | | Model | size<br><sup>(pixels) | mAP<sup>val<br>50-95 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) |
| ----------------------------------------------------------------------------------------- | --------------------- | -------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- | | ----------------------------------------------------------------------------------------- | --------------------- | -------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-oiv7.pt) | 640 | 18.4 | 142.4 | 1.21 | 3.5 | 10.5 | | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-oiv7.pt) | 640 | 18.4 | 142.4 | 1.21 | 3.5 | 10.5 |
| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-oiv7.pt) | 640 | 27.7 | 183.1 | 1.40 | 11.4 | 29.7 | | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-oiv7.pt) | 640 | 27.7 | 183.1 | 1.40 | 11.4 | 29.7 |
| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-oiv7.pt) | 640 | 33.6 | 408.5 | 2.26 | 26.2 | 80.6 | | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-oiv7.pt) | 640 | 33.6 | 408.5 | 2.26 | 26.2 | 80.6 |
| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-oiv7.pt) | 640 | 34.9 | 596.9 | 2.43 | 44.1 | 167.4 | | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-oiv7.pt) | 640 | 34.9 | 596.9 | 2.43 | 44.1 | 167.4 |
| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-oiv7.pt) | 640 | 36.3 | 860.6 | 3.56 | 68.7 | 260.6 | | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-oiv7.pt) | 640 | 36.3 | 860.6 | 3.56 | 68.7 | 260.6 |
- **mAP<sup>val</sup>** values are for single-model single-scale on [Open Image V7](https://docs.ultralytics.com/datasets/detect/open-images-v7/) dataset. <br>Reproduce by `yolo val detect data=open-images-v7.yaml device=0` - **mAP<sup>val</sup>** values are for single-model single-scale on [Open Image V7](https://docs.ultralytics.com/datasets/detect/open-images-v7/) dataset. <br>Reproduce by `yolo val detect data=open-images-v7.yaml device=0`
- **Speed** averaged over Open Image V7 val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val detect data=open-images-v7.yaml batch=1 device=0|cpu` - **Speed** averaged over Open Image V7 val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val detect data=open-images-v7.yaml batch=1 device=0|cpu`
@ -158,11 +158,11 @@ See [Segmentation Docs](https://docs.ultralytics.com/tasks/segment/) for usage e
| Model | size<br><sup>(pixels) | mAP<sup>box<br>50-95 | mAP<sup>mask<br>50-95 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) | | Model | size<br><sup>(pixels) | mAP<sup>box<br>50-95 | mAP<sup>mask<br>50-95 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) |
| -------------------------------------------------------------------------------------------- | --------------------- | -------------------- | --------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- | | -------------------------------------------------------------------------------------------- | --------------------- | -------------------- | --------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
| [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 | | [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 |
| [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 | | [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 |
| [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 | | [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 |
| [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 | | [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 |
| [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 | | [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 |
- **mAP<sup>val</sup>** values are for single-model single-scale on [COCO val2017](http://cocodataset.org) dataset. <br>Reproduce by `yolo val segment data=coco-seg.yaml device=0` - **mAP<sup>val</sup>** values are for single-model single-scale on [COCO val2017](http://cocodataset.org) dataset. <br>Reproduce by `yolo val segment data=coco-seg.yaml device=0`
- **Speed** averaged over COCO val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val segment data=coco-seg.yaml batch=1 device=0|cpu` - **Speed** averaged over COCO val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val segment data=coco-seg.yaml batch=1 device=0|cpu`
@ -175,12 +175,12 @@ See [Pose Docs](https://docs.ultralytics.com/tasks/pose/) for usage examples wit
| Model | size<br><sup>(pixels) | mAP<sup>pose<br>50-95 | mAP<sup>pose<br>50 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) | | Model | size<br><sup>(pixels) | mAP<sup>pose<br>50-95 | mAP<sup>pose<br>50 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) |
| ---------------------------------------------------------------------------------------------------- | --------------------- | --------------------- | ------------------ | ------------------------------ | ----------------------------------- | ------------------ | ----------------- | | ---------------------------------------------------------------------------------------------------- | --------------------- | --------------------- | ------------------ | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
| [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 | | [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 |
| [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 | | [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 |
| [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 | | [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 |
| [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 | | [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 |
| [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 | | [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 |
| [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 | | [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 |
- **mAP<sup>val</sup>** values are for single-model single-scale on [COCO Keypoints val2017](http://cocodataset.org) dataset. <br>Reproduce by `yolo val pose data=coco-pose.yaml device=0` - **mAP<sup>val</sup>** values are for single-model single-scale on [COCO Keypoints val2017](http://cocodataset.org) dataset. <br>Reproduce by `yolo val pose data=coco-pose.yaml device=0`
- **Speed** averaged over COCO val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val pose data=coco-pose.yaml batch=1 device=0|cpu` - **Speed** averaged over COCO val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val pose data=coco-pose.yaml batch=1 device=0|cpu`
@ -193,11 +193,11 @@ See [OBB Docs](https://docs.ultralytics.com/tasks/obb/) for usage examples with
| Model | size<br><sup>(pixels) | mAP<sup>test<br>50 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) | | Model | size<br><sup>(pixels) | mAP<sup>test<br>50 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) |
| -------------------------------------------------------------------------------------------- | --------------------- | ------------------ | ------------------------------ | ----------------------------------- | ------------------ | ----------------- | | -------------------------------------------------------------------------------------------- | --------------------- | ------------------ | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
| [YOLOv8n-obb](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-obb.pt) | 1024 | 76.9 | 204.77 | 3.57 | 3.1 | 23.3 | | [YOLOv8n-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-obb.pt) | 1024 | 76.9 | 204.77 | 3.57 | 3.1 | 23.3 |
| [YOLOv8s-obb](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-obb.pt) | 1024 | 78.0 | 424.88 | 4.07 | 11.4 | 76.3 | | [YOLOv8s-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-obb.pt) | 1024 | 78.0 | 424.88 | 4.07 | 11.4 | 76.3 |
| [YOLOv8m-obb](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-obb.pt) | 1024 | 80.5 | 763.48 | 7.61 | 26.4 | 208.6 | | [YOLOv8m-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-obb.pt) | 1024 | 80.5 | 763.48 | 7.61 | 26.4 | 208.6 |
| [YOLOv8l-obb](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-obb.pt) | 1024 | 80.7 | 1278.42 | 11.83 | 44.5 | 433.8 | | [YOLOv8l-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-obb.pt) | 1024 | 80.7 | 1278.42 | 11.83 | 44.5 | 433.8 |
| [YOLOv8x-obb](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-obb.pt) | 1024 | 81.36 | 1759.10 | 13.23 | 69.5 | 676.7 | | [YOLOv8x-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-obb.pt) | 1024 | 81.36 | 1759.10 | 13.23 | 69.5 | 676.7 |
- **mAP<sup>test</sup>** values are for single-model multi-scale on [DOTAv1](https://captain-whu.github.io/DOTA/index.html) dataset. <br>Reproduce by `yolo val obb data=DOTAv1.yaml device=0 split=test` and submit merged results to [DOTA evaluation](https://captain-whu.github.io/DOTA/evaluation.html). - **mAP<sup>test</sup>** values are for single-model multi-scale on [DOTAv1](https://captain-whu.github.io/DOTA/index.html) dataset. <br>Reproduce by `yolo val obb data=DOTAv1.yaml device=0 split=test` and submit merged results to [DOTA evaluation](https://captain-whu.github.io/DOTA/evaluation.html).
- **Speed** averaged over DOTAv1 val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val obb data=DOTAv1.yaml batch=1 device=0|cpu` - **Speed** averaged over DOTAv1 val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val obb data=DOTAv1.yaml batch=1 device=0|cpu`
@ -210,11 +210,11 @@ See [Classification Docs](https://docs.ultralytics.com/tasks/classify/) for usag
| Model | size<br><sup>(pixels) | acc<br><sup>top1 | acc<br><sup>top5 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) at 640 | | Model | size<br><sup>(pixels) | acc<br><sup>top1 | acc<br><sup>top5 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) at 640 |
| -------------------------------------------------------------------------------------------- | --------------------- | ---------------- | ---------------- | ------------------------------ | ----------------------------------- | ------------------ | ------------------------ | | -------------------------------------------------------------------------------------------- | --------------------- | ---------------- | ---------------- | ------------------------------ | ----------------------------------- | ------------------ | ------------------------ |
| [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-cls.pt) | 224 | 69.0 | 88.3 | 12.9 | 0.31 | 2.7 | 4.3 | | [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-cls.pt) | 224 | 69.0 | 88.3 | 12.9 | 0.31 | 2.7 | 4.3 |
| [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-cls.pt) | 224 | 73.8 | 91.7 | 23.4 | 0.35 | 6.4 | 13.5 | | [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-cls.pt) | 224 | 73.8 | 91.7 | 23.4 | 0.35 | 6.4 | 13.5 |
| [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-cls.pt) | 224 | 76.8 | 93.5 | 85.4 | 0.62 | 17.0 | 42.7 | | [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-cls.pt) | 224 | 76.8 | 93.5 | 85.4 | 0.62 | 17.0 | 42.7 |
| [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-cls.pt) | 224 | 76.8 | 93.5 | 163.0 | 0.87 | 37.5 | 99.7 | | [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-cls.pt) | 224 | 76.8 | 93.5 | 163.0 | 0.87 | 37.5 | 99.7 |
| [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-cls.pt) | 224 | 79.0 | 94.6 | 232.0 | 1.01 | 57.4 | 154.8 | | [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-cls.pt) | 224 | 79.0 | 94.6 | 232.0 | 1.01 | 57.4 | 154.8 |
- **acc** values are model accuracies on the [ImageNet](https://www.image-net.org/) dataset validation set. <br>Reproduce by `yolo val classify data=path/to/ImageNet device=0` - **acc** values are model accuracies on the [ImageNet](https://www.image-net.org/) dataset validation set. <br>Reproduce by `yolo val classify data=path/to/ImageNet device=0`
- **Speed** averaged over ImageNet val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val classify data=path/to/ImageNet batch=1 device=0|cpu` - **Speed** averaged over ImageNet val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val classify data=path/to/ImageNet batch=1 device=0|cpu`

62
README.zh-CN.md
View File

@ -126,11 +126,11 @@ Ultralytics 提供了 YOLOv8 的交互式笔记本，涵盖训练、验证、跟
| 模型 | 尺寸<br><sup>(像素) | mAP<sup>val<br>50-95 | 速度<br><sup>CPU ONNX<br>(ms) | 速度<br><sup>A100 TensorRT<br>(ms) | 参数<br><sup>(M) | FLOPs<br><sup>(B) | | 模型 | 尺寸<br><sup>(像素) | mAP<sup>val<br>50-95 | 速度<br><sup>CPU ONNX<br>(ms) | 速度<br><sup>A100 TensorRT<br>(ms) | 参数<br><sup>(M) | FLOPs<br><sup>(B) |
| ------------------------------------------------------------------------------------ | --------------- | -------------------- | --------------------------- | -------------------------------- | -------------- | ----------------- | | ------------------------------------------------------------------------------------ | --------------- | -------------------- | --------------------------- | -------------------------------- | -------------- | ----------------- |
| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 | | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 |
| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 | | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 |
| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 | | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 |
| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 | | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 |
| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 | | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 |
- **mAP<sup>val</sup>** 值是基于单模型单尺度在 [COCO val2017](http://cocodataset.org) 数据集上的结果。 <br>通过 `yolo val detect data=coco.yaml device=0` 复现 - **mAP<sup>val</sup>** 值是基于单模型单尺度在 [COCO val2017](http://cocodataset.org) 数据集上的结果。 <br>通过 `yolo val detect data=coco.yaml device=0` 复现
- **速度** 是使用 [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) 实例对 COCO val 图像进行平均计算的。 <br>通过 `yolo val detect data=coco.yaml batch=1 device=0|cpu` 复现 - **速度** 是使用 [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) 实例对 COCO val 图像进行平均计算的。 <br>通过 `yolo val detect data=coco.yaml batch=1 device=0|cpu` 复现
@ -143,11 +143,11 @@ Ultralytics 提供了 YOLOv8 的交互式笔记本，涵盖训练、验证、跟
| 模型 | 尺寸<br><sup>(像素) | mAP<sup>验证<br>50-95 | 速度<br><sup>CPU ONNX<br>(毫秒) | 速度<br><sup>A100 TensorRT<br>(毫秒) | 参数<br><sup>(M) | 浮点运算<br><sup>(B) | | 模型 | 尺寸<br><sup>(像素) | mAP<sup>验证<br>50-95 | 速度<br><sup>CPU ONNX<br>(毫秒) | 速度<br><sup>A100 TensorRT<br>(毫秒) | 参数<br><sup>(M) | 浮点运算<br><sup>(B) |
| ----------------------------------------------------------------------------------------- | --------------- | ------------------- | --------------------------- | -------------------------------- | -------------- | ---------------- | | ----------------------------------------------------------------------------------------- | --------------- | ------------------- | --------------------------- | -------------------------------- | -------------- | ---------------- |
| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-oiv7.pt) | 640 | 18.4 | 142.4 | 1.21 | 3.5 | 10.5 | | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-oiv7.pt) | 640 | 18.4 | 142.4 | 1.21 | 3.5 | 10.5 |
| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-oiv7.pt) | 640 | 27.7 | 183.1 | 1.40 | 11.4 | 29.7 | | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-oiv7.pt) | 640 | 27.7 | 183.1 | 1.40 | 11.4 | 29.7 |
| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-oiv7.pt) | 640 | 33.6 | 408.5 | 2.26 | 26.2 | 80.6 | | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-oiv7.pt) | 640 | 33.6 | 408.5 | 2.26 | 26.2 | 80.6 |
| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-oiv7.pt) | 640 | 34.9 | 596.9 | 2.43 | 44.1 | 167.4 | | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-oiv7.pt) | 640 | 34.9 | 596.9 | 2.43 | 44.1 | 167.4 |
| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-oiv7.pt) | 640 | 36.3 | 860.6 | 3.56 | 68.7 | 260.6 | | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-oiv7.pt) | 640 | 36.3 | 860.6 | 3.56 | 68.7 | 260.6 |
- **mAP<sup>验证</sup>** 值适用于在[Open Image V7](https://docs.ultralytics.com/datasets/detect/open-images-v7/)数据集上的单模型单尺度。 <br>通过 `yolo val detect data=open-images-v7.yaml device=0` 以复现。 - **mAP<sup>验证</sup>** 值适用于在[Open Image V7](https://docs.ultralytics.com/datasets/detect/open-images-v7/)数据集上的单模型单尺度。 <br>通过 `yolo val detect data=open-images-v7.yaml device=0` 以复现。
- **速度** 在使用[Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/)实例对Open Image V7验证图像进行平均测算。 <br>通过 `yolo val detect data=open-images-v7.yaml batch=1 device=0|cpu` 以复现。 - **速度** 在使用[Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/)实例对Open Image V7验证图像进行平均测算。 <br>通过 `yolo val detect data=open-images-v7.yaml batch=1 device=0|cpu` 以复现。
@ -160,11 +160,11 @@ Ultralytics 提供了 YOLOv8 的交互式笔记本，涵盖训练、验证、跟
| 模型 | 尺寸<br><sup>(像素) | mAP<sup>box<br>50-95 | mAP<sup>mask<br>50-95 | 速度<br><sup>CPU ONNX<br>(ms) | 速度<br><sup>A100 TensorRT<br>(ms) | 参数<br><sup>(M) | FLOPs<br><sup>(B) | | 模型 | 尺寸<br><sup>(像素) | mAP<sup>box<br>50-95 | mAP<sup>mask<br>50-95 | 速度<br><sup>CPU ONNX<br>(ms) | 速度<br><sup>A100 TensorRT<br>(ms) | 参数<br><sup>(M) | FLOPs<br><sup>(B) |
| -------------------------------------------------------------------------------------------- | --------------- | -------------------- | --------------------- | --------------------------- | -------------------------------- | -------------- | ----------------- | | -------------------------------------------------------------------------------------------- | --------------- | -------------------- | --------------------- | --------------------------- | -------------------------------- | -------------- | ----------------- |
| [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 | | [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 |
| [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 | | [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 |
| [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 | | [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 |
| [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 | | [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 |
| [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 | | [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 |
- **mAP<sup>val</sup>** 值是基于单模型单尺度在 [COCO val2017](http://cocodataset.org) 数据集上的结果。 <br>通过 `yolo val segment data=coco-seg.yaml device=0` 复现 - **mAP<sup>val</sup>** 值是基于单模型单尺度在 [COCO val2017](http://cocodataset.org) 数据集上的结果。 <br>通过 `yolo val segment data=coco-seg.yaml device=0` 复现
- **速度** 是使用 [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) 实例对 COCO val 图像进行平均计算的。 <br>通过 `yolo val segment data=coco-seg.yaml batch=1 device=0|cpu` 复现 - **速度** 是使用 [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) 实例对 COCO val 图像进行平均计算的。 <br>通过 `yolo val segment data=coco-seg.yaml batch=1 device=0|cpu` 复现
@ -177,12 +177,12 @@ Ultralytics 提供了 YOLOv8 的交互式笔记本，涵盖训练、验证、跟
| 模型 | 尺寸<br><sup>(像素) | mAP<sup>pose<br>50-95 | mAP<sup>pose<br>50 | 速度<br><sup>CPU ONNX<br>(ms) | 速度<br><sup>A100 TensorRT<br>(ms) | 参数<br><sup>(M) | FLOPs<br><sup>(B) | | 模型 | 尺寸<br><sup>(像素) | mAP<sup>pose<br>50-95 | mAP<sup>pose<br>50 | 速度<br><sup>CPU ONNX<br>(ms) | 速度<br><sup>A100 TensorRT<br>(ms) | 参数<br><sup>(M) | FLOPs<br><sup>(B) |
| ---------------------------------------------------------------------------------------------------- | --------------- | --------------------- | ------------------ | --------------------------- | -------------------------------- | -------------- | ----------------- | | ---------------------------------------------------------------------------------------------------- | --------------- | --------------------- | ------------------ | --------------------------- | -------------------------------- | -------------- | ----------------- |
| [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 | | [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 |
| [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 | | [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 |
| [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 | | [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 |
| [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 | | [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 |
| [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 | | [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 |
| [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 | | [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 |
- **mAP<sup>val</sup>** 值是基于单模型单尺度在 [COCO Keypoints val2017](http://cocodataset.org) 数据集上的结果。 <br>通过 `yolo val pose data=coco-pose.yaml device=0` 复现 - **mAP<sup>val</sup>** 值是基于单模型单尺度在 [COCO Keypoints val2017](http://cocodataset.org) 数据集上的结果。 <br>通过 `yolo val pose data=coco-pose.yaml device=0` 复现
- **速度** 是使用 [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) 实例对 COCO val 图像进行平均计算的。 <br>通过 `yolo val pose data=coco-pose.yaml batch=1 device=0|cpu` 复现 - **速度** 是使用 [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) 实例对 COCO val 图像进行平均计算的。 <br>通过 `yolo val pose data=coco-pose.yaml batch=1 device=0|cpu` 复现
@ -195,11 +195,11 @@ Ultralytics 提供了 YOLOv8 的交互式笔记本，涵盖训练、验证、跟
| 模型 | 尺寸<br><sup>(像素) | mAP<sup>test<br>50 | 速度<br><sup>CPU ONNX<br>(ms) | 速度<br><sup>A100 TensorRT<br>(ms) | 参数<br><sup>(M) | FLOPs<br><sup>(B) | | 模型 | 尺寸<br><sup>(像素) | mAP<sup>test<br>50 | 速度<br><sup>CPU ONNX<br>(ms) | 速度<br><sup>A100 TensorRT<br>(ms) | 参数<br><sup>(M) | FLOPs<br><sup>(B) |
| -------------------------------------------------------------------------------------------- | --------------- | ------------------ | --------------------------- | -------------------------------- | -------------- | ----------------- | | -------------------------------------------------------------------------------------------- | --------------- | ------------------ | --------------------------- | -------------------------------- | -------------- | ----------------- |
| [YOLOv8n-obb](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-obb.pt) | 1024 | 76.9 | 204.77 | 3.57 | 3.1 | 23.3 | | [YOLOv8n-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-obb.pt) | 1024 | 76.9 | 204.77 | 3.57 | 3.1 | 23.3 |
| [YOLOv8s-obb](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-obb.pt) | 1024 | 78.0 | 424.88 | 4.07 | 11.4 | 76.3 | | [YOLOv8s-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-obb.pt) | 1024 | 78.0 | 424.88 | 4.07 | 11.4 | 76.3 |
| [YOLOv8m-obb](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-obb.pt) | 1024 | 80.5 | 763.48 | 7.61 | 26.4 | 208.6 | | [YOLOv8m-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-obb.pt) | 1024 | 80.5 | 763.48 | 7.61 | 26.4 | 208.6 |
| [YOLOv8l-obb](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-obb.pt) | 1024 | 80.7 | 1278.42 | 11.83 | 44.5 | 433.8 | | [YOLOv8l-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-obb.pt) | 1024 | 80.7 | 1278.42 | 11.83 | 44.5 | 433.8 |
| [YOLOv8x-obb](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-obb.pt) | 1024 | 81.36 | 1759.10 | 13.23 | 69.5 | 676.7 | | [YOLOv8x-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-obb.pt) | 1024 | 81.36 | 1759.10 | 13.23 | 69.5 | 676.7 |
- **mAP<sup>val</sup>** 值是基于单模型多尺度在 [DOTAv1](https://captain-whu.github.io/DOTA/index.html) 数据集上的结果。 <br>通过 `yolo val obb data=DOTAv1.yaml device=0 split=test` 复现 - **mAP<sup>val</sup>** 值是基于单模型多尺度在 [DOTAv1](https://captain-whu.github.io/DOTA/index.html) 数据集上的结果。 <br>通过 `yolo val obb data=DOTAv1.yaml device=0 split=test` 复现
- **速度** 是使用 [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) 实例对 COCO val 图像进行平均计算的。 <br>通过 `yolo val obb data=DOTAv1.yaml batch=1 device=0|cpu` 复现 - **速度** 是使用 [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) 实例对 COCO val 图像进行平均计算的。 <br>通过 `yolo val obb data=DOTAv1.yaml batch=1 device=0|cpu` 复现
@ -212,11 +212,11 @@ Ultralytics 提供了 YOLOv8 的交互式笔记本，涵盖训练、验证、跟
| 模型 | 尺寸<br><sup>(像素) | acc<br><sup>top1 | acc<br><sup>top5 | 速度<br><sup>CPU ONNX<br>(ms) | 速度<br><sup>A100 TensorRT<br>(ms) | 参数<br><sup>(M) | FLOPs<br><sup>(B) at 640 | | 模型 | 尺寸<br><sup>(像素) | acc<br><sup>top1 | acc<br><sup>top5 | 速度<br><sup>CPU ONNX<br>(ms) | 速度<br><sup>A100 TensorRT<br>(ms) | 参数<br><sup>(M) | FLOPs<br><sup>(B) at 640 |
| -------------------------------------------------------------------------------------------- | --------------- | ---------------- | ---------------- | --------------------------- | -------------------------------- | -------------- | ------------------------ | | -------------------------------------------------------------------------------------------- | --------------- | ---------------- | ---------------- | --------------------------- | -------------------------------- | -------------- | ------------------------ |
| [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-cls.pt) | 224 | 69.0 | 88.3 | 12.9 | 0.31 | 2.7 | 4.3 | | [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-cls.pt) | 224 | 69.0 | 88.3 | 12.9 | 0.31 | 2.7 | 4.3 |
| [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-cls.pt) | 224 | 73.8 | 91.7 | 23.4 | 0.35 | 6.4 | 13.5 | | [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-cls.pt) | 224 | 73.8 | 91.7 | 23.4 | 0.35 | 6.4 | 13.5 |
| [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-cls.pt) | 224 | 76.8 | 93.5 | 85.4 | 0.62 | 17.0 | 42.7 | | [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-cls.pt) | 224 | 76.8 | 93.5 | 85.4 | 0.62 | 17.0 | 42.7 |
| [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-cls.pt) | 224 | 76.8 | 93.5 | 163.0 | 0.87 | 37.5 | 99.7 | | [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-cls.pt) | 224 | 76.8 | 93.5 | 163.0 | 0.87 | 37.5 | 99.7 |
| [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-cls.pt) | 224 | 79.0 | 94.6 | 232.0 | 1.01 | 57.4 | 154.8 | | [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-cls.pt) | 224 | 79.0 | 94.6 | 232.0 | 1.01 | 57.4 | 154.8 |
- **acc** 值是模型在 [ImageNet](https://www.image-net.org/) 数据集验证集上的准确率。 <br>通过 `yolo val classify data=path/to/ImageNet device=0` 复现 - **acc** 值是模型在 [ImageNet](https://www.image-net.org/) 数据集验证集上的准确率。 <br>通过 `yolo val classify data=path/to/ImageNet device=0` 复现
- **速度** 是使用 [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) 实例对 ImageNet val 图像进行平均计算的。 <br>通过 `yolo val classify data=path/to/ImageNet batch=1 device=0|cpu` 复现 - **速度** 是使用 [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) 实例对 ImageNet val 图像进行平均计算的。 <br>通过 `yolo val classify data=path/to/ImageNet batch=1 device=0|cpu` 复现

2
docker/Dockerfile
View File

@ -24,7 +24,7 @@ WORKDIR /usr/src/ultralytics
# Copy contents # Copy contents
# COPY . /usr/src/ultralytics # git permission issues inside container # COPY . /usr/src/ultralytics # git permission issues inside container
RUN git clone https://github.com/ultralytics/ultralytics -b main /usr/src/ultralytics RUN git clone https://github.com/ultralytics/ultralytics -b main /usr/src/ultralytics
ADD https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt /usr/src/ultralytics/ ADD https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt /usr/src/ultralytics/
# Install pip packages # Install pip packages
RUN python3 -m pip install --upgrade pip wheel RUN python3 -m pip install --upgrade pip wheel

2
docker/Dockerfile-arm64
View File

@ -19,7 +19,7 @@ WORKDIR /usr/src/ultralytics
# Copy contents # Copy contents
# COPY . /usr/src/ultralytics # git permission issues inside container # COPY . /usr/src/ultralytics # git permission issues inside container
RUN git clone https://github.com/ultralytics/ultralytics -b main /usr/src/ultralytics RUN git clone https://github.com/ultralytics/ultralytics -b main /usr/src/ultralytics
ADD https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt /usr/src/ultralytics/ ADD https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt /usr/src/ultralytics/
# Install pip packages # Install pip packages
RUN python3 -m pip install --upgrade pip wheel RUN python3 -m pip install --upgrade pip wheel

2
docker/Dockerfile-conda
View File

@ -13,7 +13,7 @@ RUN apt update \
&& apt install --no-install-recommends -y libgl1 && apt install --no-install-recommends -y libgl1
# Copy contents # Copy contents
ADD https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt . ADD https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt .
# Install conda packages # Install conda packages
# mkl required to fix 'OSError: libmkl_intel_lp64.so.2: cannot open shared object file: No such file or directory' # mkl required to fix 'OSError: libmkl_intel_lp64.so.2: cannot open shared object file: No such file or directory'

2
docker/Dockerfile-cpu
View File

@ -19,7 +19,7 @@ WORKDIR /usr/src/ultralytics
# Copy contents # Copy contents
# COPY . /usr/src/ultralytics # git permission issues inside container # COPY . /usr/src/ultralytics # git permission issues inside container
RUN git clone https://github.com/ultralytics/ultralytics -b main /usr/src/ultralytics RUN git clone https://github.com/ultralytics/ultralytics -b main /usr/src/ultralytics
ADD https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt /usr/src/ultralytics/ ADD https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt /usr/src/ultralytics/
# Remove python3.11/EXTERNALLY-MANAGED or use 'pip install --break-system-packages' avoid 'externally-managed-environment' Ubuntu nightly error # Remove python3.11/EXTERNALLY-MANAGED or use 'pip install --break-system-packages' avoid 'externally-managed-environment' Ubuntu nightly error
RUN rm -rf /usr/lib/python3.11/EXTERNALLY-MANAGED RUN rm -rf /usr/lib/python3.11/EXTERNALLY-MANAGED

2
docker/Dockerfile-jetson
View File

@ -19,7 +19,7 @@ WORKDIR /usr/src/ultralytics
# Copy contents # Copy contents
# COPY . /usr/src/ultralytics # git permission issues inside container # COPY . /usr/src/ultralytics # git permission issues inside container
RUN git clone https://github.com/ultralytics/ultralytics -b main /usr/src/ultralytics RUN git clone https://github.com/ultralytics/ultralytics -b main /usr/src/ultralytics
ADD https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt /usr/src/ultralytics/ ADD https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt /usr/src/ultralytics/
# Remove opencv-python from Ultralytics dependencies as it conflicts with opencv-python installed in base image # Remove opencv-python from Ultralytics dependencies as it conflicts with opencv-python installed in base image
RUN grep -v "opencv-python" pyproject.toml > temp.toml && mv temp.toml pyproject.toml RUN grep -v "opencv-python" pyproject.toml > temp.toml && mv temp.toml pyproject.toml

2
docker/Dockerfile-python
View File

@ -19,7 +19,7 @@ WORKDIR /usr/src/ultralytics
# Copy contents # Copy contents
# COPY . /usr/src/ultralytics # git permission issues inside container # COPY . /usr/src/ultralytics # git permission issues inside container
RUN git clone https://github.com/ultralytics/ultralytics -b main /usr/src/ultralytics RUN git clone https://github.com/ultralytics/ultralytics -b main /usr/src/ultralytics
ADD https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt /usr/src/ultralytics/ ADD https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt /usr/src/ultralytics/
# Remove python3.11/EXTERNALLY-MANAGED or use 'pip install --break-system-packages' avoid 'externally-managed-environment' Ubuntu nightly error # Remove python3.11/EXTERNALLY-MANAGED or use 'pip install --break-system-packages' avoid 'externally-managed-environment' Ubuntu nightly error
# RUN rm -rf /usr/lib/python3.11/EXTERNALLY-MANAGED # RUN rm -rf /usr/lib/python3.11/EXTERNALLY-MANAGED

6
docs/ar/models/yolo-nas.md
View File

@ -92,9 +92,9 @@ keywords: YOLO-NAS, Deci AI, كشف الكائنات, deep learning, البحث
| نوع النموذج | أوزان مدربة مسبقًا | المهام المدعومة | الاستدلال | التحقق | التدريب | التصدير | | نوع النموذج | أوزان مدربة مسبقًا | المهام المدعومة | الاستدلال | التحقق | التدريب | التصدير |
|-------------|-----------------------------------------------------------------------------------------------|------------------------------------|-----------|--------|---------|---------| |-------------|-----------------------------------------------------------------------------------------------|------------------------------------|-----------|--------|---------|---------|
| YOLO-NAS-s | [yolo_nas_s.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolo_nas_s.pt) | [كشف الكائنات](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ | | YOLO-NAS-s | [yolo_nas_s.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolo_nas_s.pt) | [كشف الكائنات](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ |
| YOLO-NAS-m | [yolo_nas_m.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolo_nas_m.pt) | [كشف الكائنات](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ | | YOLO-NAS-m | [yolo_nas_m.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolo_nas_m.pt) | [كشف الكائنات](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ |
| YOLO-NAS-l | [yolo_nas_l.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolo_nas_l.pt) | [كشف الكائنات](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ | | YOLO-NAS-l | [yolo_nas_l.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolo_nas_l.pt) | [كشف الكائنات](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ |
## الاقتباسات والشكر ## الاقتباسات والشكر

20
docs/ar/models/yolov5.md
View File

@ -40,17 +40,17 @@ keywords: YOLOv5u، كشف الكائنات، النماذج المدربة مس
| النموذج | يامل | حجم<br><sup>(بكسل) | mAP<sup>val<br>50-95 | سرعة<br><sup>معالج الجهاز ONNX<br>(مللي ثانية) | سرعة<br><sup>حويصلة A100 TensorRT<br>(مللي ثانية) | المعلمات<br><sup>(مليون) | FLOPs<br><sup>(بليون) | | النموذج | يامل | حجم<br><sup>(بكسل) | mAP<sup>val<br>50-95 | سرعة<br><sup>معالج الجهاز ONNX<br>(مللي ثانية) | سرعة<br><sup>حويصلة A100 TensorRT<br>(مللي ثانية) | المعلمات<br><sup>(مليون) | FLOPs<br><sup>(بليون) |
|---------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------|-----------------------|----------------------|--------------------------------|-------------------------------------|--------------------|-------------------| |---------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------|-----------------------|----------------------|--------------------------------|-------------------------------------|--------------------|-------------------|
| [yolov5nu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5nu.pt) | [yolov5n.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 34.3 | 73.6 | 1.06 | 2.6 | 7.7 | | [yolov5nu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5nu.pt) | [yolov5n.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 34.3 | 73.6 | 1.06 | 2.6 | 7.7 |
| [yolov5su.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5su.pt) | [yolov5s.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 43.0 | 120.7 | 1.27 | 9.1 | 24.0 | | [yolov5su.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5su.pt) | [yolov5s.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 43.0 | 120.7 | 1.27 | 9.1 | 24.0 |
| [yolov5mu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5mu.pt) | [yolov5m.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 49.0 | 233.9 | 1.86 | 25.1 | 64.2 | | [yolov5mu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5mu.pt) | [yolov5m.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 49.0 | 233.9 | 1.86 | 25.1 | 64.2 |
| [yolov5lu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5lu.pt) | [yolov5l.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 52.2 | 408.4 | 2.50 | 53.2 | 135.0 | | [yolov5lu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5lu.pt) | [yolov5l.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 52.2 | 408.4 | 2.50 | 53.2 | 135.0 |
| [yolov5xu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5xu.pt) | [yolov5x.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 53.2 | 763.2 | 3.81 | 97.2 | 246.4 | | [yolov5xu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5xu.pt) | [yolov5x.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 53.2 | 763.2 | 3.81 | 97.2 | 246.4 |
| | | | | | | | | | | | | | | | | |
| [yolov5n6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5n6u.pt) | [yolov5n6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 42.1 | 211.0 | 1.83 | 4.3 | 7.8 | | [yolov5n6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5n6u.pt) | [yolov5n6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 42.1 | 211.0 | 1.83 | 4.3 | 7.8 |
| [yolov5s6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5s6u.pt) | [yolov5s6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 48.6 | 422.6 | 2.34 | 15.3 | 24.6 | | [yolov5s6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5s6u.pt) | [yolov5s6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 48.6 | 422.6 | 2.34 | 15.3 | 24.6 |
| [yolov5m6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5m6u.pt) | [yolov5m6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 53.6 | 810.9 | 4.36 | 41.2 | 65.7 | | [yolov5m6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5m6u.pt) | [yolov5m6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 53.6 | 810.9 | 4.36 | 41.2 | 65.7 |
| [yolov5l6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5l6u.pt) | [yolov5l6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 55.7 | 1470.9 | 5.47 | 86.1 | 137.4 | | [yolov5l6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5l6u.pt) | [yolov5l6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 55.7 | 1470.9 | 5.47 | 86.1 | 137.4 |
| [yolov5x6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5x6u.pt) | [yolov5x6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 56.8 | 2436.5 | 8.98 | 155.4 | 250.7 | | [yolov5x6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5x6u.pt) | [yolov5x6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 56.8 | 2436.5 | 8.98 | 155.4 | 250.7 |
## أمثلة للاستخدام ## أمثلة للاستخدام

52
docs/ar/models/yolov8.md
View File

@ -44,11 +44,11 @@ YOLOv8 هو التطور الأخير في سلسلة YOLO لمكتشفات ال
| النموذج | حجم<br><sup>(بيكسل) | معدل الكشف<sup>التحقق<br>50-95 | سرعة<br><sup>CPU ONNX<br>(متوسط) | سرعة<br><sup>A100 TensorRT<br>(متوسط) | معلمات<br><sup>(مليون) | FLOPs<br><sup>(مليون) | | النموذج | حجم<br><sup>(بيكسل) | معدل الكشف<sup>التحقق<br>50-95 | سرعة<br><sup>CPU ONNX<br>(متوسط) | سرعة<br><sup>A100 TensorRT<br>(متوسط) | معلمات<br><sup>(مليون) | FLOPs<br><sup>(مليون) |
| ------------------------------------------------------------------------------------ | --------------------- | -------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- | | ------------------------------------------------------------------------------------ | --------------------- | -------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 | | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 |
| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 | | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 |
| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 | | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 |
| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 | | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 |
| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 | | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 |
=== "الكشف (صور مفتوحة V7)" === "الكشف (صور مفتوحة V7)"
@ -56,11 +56,11 @@ YOLOv8 هو التطور الأخير في سلسلة YOLO لمكتشفات ال
| النموذج | حجم<br><sup>(بيكسل) | معدل الكشف<sup>التحقق<br>50-95 | سرعة<br><sup>CPU ONNX<br>(متوسط) | سرعة<br><sup>A100 TensorRT<br>(متوسط) | معلمات<br><sup>(مليون) | FLOPs<br><sup>(مليون) | | النموذج | حجم<br><sup>(بيكسل) | معدل الكشف<sup>التحقق<br>50-95 | سرعة<br><sup>CPU ONNX<br>(متوسط) | سرعة<br><sup>A100 TensorRT<br>(متوسط) | معلمات<br><sup>(مليون) | FLOPs<br><sup>(مليون) |
| ----------------------------------------------------------------------------------------- | --------------------- | -------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- | | ----------------------------------------------------------------------------------------- | --------------------- | -------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-oiv7.pt) | 640 | 18.4 | 142.4 | 1.21 | 3.5 | 10.5 | | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-oiv7.pt) | 640 | 18.4 | 142.4 | 1.21 | 3.5 | 10.5 |
| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-oiv7.pt) | 640 | 27.7 | 183.1 | 1.40 | 11.4 | 29.7 | | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-oiv7.pt) | 640 | 27.7 | 183.1 | 1.40 | 11.4 | 29.7 |
| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-oiv7.pt) | 640 | 33.6 | 408.5 | 2.26 | 26.2 | 80.6 | | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-oiv7.pt) | 640 | 33.6 | 408.5 | 2.26 | 26.2 | 80.6 |
| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-oiv7.pt) | 640 | 34.9 | 596.9 | 2.43 | 44.1 | 167.4 | | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-oiv7.pt) | 640 | 34.9 | 596.9 | 2.43 | 44.1 | 167.4 |
| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-oiv7.pt) | 640 | 36.3 | 860.6 | 3.56 | 68.7 | 260.6 | | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-oiv7.pt) | 640 | 36.3 | 860.6 | 3.56 | 68.7 | 260.6 |
=== "تقسيم الصور إلى أجزاء (COCO)" === "تقسيم الصور إلى أجزاء (COCO)"
@ -68,11 +68,11 @@ YOLOv8 هو التطور الأخير في سلسلة YOLO لمكتشفات ال
| النموذج | حجم<br><sup>(بيكسل) | معدل التقسيم<sup>التحقق<br>50-95 | معدل التقسيم<sup>الأقنعة<br>50-95 | سرعة<br><sup>CPU ONNX<br>(متوسط) | سرعة<br><sup>A100 TensorRT<br>(متوسط) | معلمات<br><sup>(مليون) | FLOPs<br><sup>(مليون) | | النموذج | حجم<br><sup>(بيكسل) | معدل التقسيم<sup>التحقق<br>50-95 | معدل التقسيم<sup>الأقنعة<br>50-95 | سرعة<br><sup>CPU ONNX<br>(متوسط) | سرعة<br><sup>A100 TensorRT<br>(متوسط) | معلمات<br><sup>(مليون) | FLOPs<br><sup>(مليون) |
| -------------------------------------------------------------------------------------------- | --------------------- | -------------------- | -------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- | | -------------------------------------------------------------------------------------------- | --------------------- | -------------------- | -------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
| [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 | | [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 |
| [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 | | [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 |
| [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 | | [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 |
| [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 | | [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 |
| [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 | | [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 |
=== "التصنيف (ImageNet)" === "التصنيف (ImageNet)"
@ -80,11 +80,11 @@ YOLOv8 هو التطور الأخير في سلسلة YOLO لمكتشفات ال
| النموذج | حجم<br><sup>(بيكسل) | دقة أعلى<br><sup>أعلى 1 | دقة أعلى<br><sup>أعلى 5 | سرعة<br><sup>CPU ONNX<br>(متوسط) | سرعة<br><sup>A100 TensorRT<br>(متوسط) | معلمات<br><sup>(مليون) | FLOPs<br><sup>(مليون) عند 640 | | النموذج | حجم<br><sup>(بيكسل) | دقة أعلى<br><sup>أعلى 1 | دقة أعلى<br><sup>أعلى 5 | سرعة<br><sup>CPU ONNX<br>(متوسط) | سرعة<br><sup>A100 TensorRT<br>(متوسط) | معلمات<br><sup>(مليون) | FLOPs<br><sup>(مليون) عند 640 |
| -------------------------------------------------------------------------------------------- | --------------------- | ---------------- | ---------------- | ------------------------------ | ----------------------------------- | ------------------ | ------------------------ | | -------------------------------------------------------------------------------------------- | --------------------- | ---------------- | ---------------- | ------------------------------ | ----------------------------------- | ------------------ | ------------------------ |
| [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-cls.pt) | 224 | 66.6 | 87.0 | 12.9 | 0.31 | 2.7 | 4.3 | | [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-cls.pt) | 224 | 66.6 | 87.0 | 12.9 | 0.31 | 2.7 | 4.3 |
| [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-cls.pt) | 224 | 72.3 | 91.1 | 23.4 | 0.35 | 6.4 | 13.5 | | [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-cls.pt) | 224 | 72.3 | 91.1 | 23.4 | 0.35 | 6.4 | 13.5 |
| [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-cls.pt) | 224 | 76.4 | 93.2 | 85.4 | 0.62 | 17.0 | 42.7 | | [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-cls.pt) | 224 | 76.4 | 93.2 | 85.4 | 0.62 | 17.0 | 42.7 |
| [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-cls.pt) | 224 | 78.0 | 94.1 | 163.0 | 0.87 | 37.5 | 99.7 | | [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-cls.pt) | 224 | 78.0 | 94.1 | 163.0 | 0.87 | 37.5 | 99.7 |
| [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-cls.pt) | 224 | 78.4 | 94.3 | 232.0 | 1.01 | 57.4 | 154.8 | | [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-cls.pt) | 224 | 78.4 | 94.3 | 232.0 | 1.01 | 57.4 | 154.8 |
=== "المواقف (COCO)" === "المواقف (COCO)"
@ -92,12 +92,12 @@ YOLOv8 هو التطور الأخير في سلسلة YOLO لمكتشفات ال
| النموذج | حجم<br><sup>(بيكسل) | معدل التوضيح<sup>التحقق<br>50-95 | معدل التوضيح<sup>50 | سرعة<br><sup>CPU ONNX<br>(متوسط) | سرعة<br><sup>A100 TensorRT<br>(متوسط) | معلمات<br><sup>(مليون) | FLOPs<br><sup>(مليون) | | النموذج | حجم<br><sup>(بيكسل) | معدل التوضيح<sup>التحقق<br>50-95 | معدل التوضيح<sup>50 | سرعة<br><sup>CPU ONNX<br>(متوسط) | سرعة<br><sup>A100 TensorRT<br>(متوسط) | معلمات<br><sup>(مليون) | FLOPs<br><sup>(مليون) |
| ---------------------------------------------------------------------------------------------------- | --------------------- | --------------------- | ------------------ | ------------------------------ | ----------------------------------- | ------------------ | ----------------- | | ---------------------------------------------------------------------------------------------------- | --------------------- | --------------------- | ------------------ | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
| [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 | | [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 |
| [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 | | [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 |
| [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 | | [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 |
| [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 | | [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 |
| [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 | | [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 |
| [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 | | [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 |
## أمثلة استخدام ## أمثلة استخدام

10
docs/ar/tasks/classify.md
View File

@ -24,11 +24,11 @@ keywords: Ultralytics، YOLOv8، تصنيف الصور، النماذج المد
| النموذج | الحجم<br><sup>(بكسل) | دقة (أعلى 1)<br><sup>acc | دقة (أعلى 5)<br><sup>acc | سرعة التنفيذ<br><sup>ONNX للوحدة المركزية<br>(مللي ثانية) | سرعة التنفيذ<br><sup>A100 TensorRT<br>(مللي ثانية) | المعلمات<br><sup>(مليون) | FLOPs<br><sup>(مليار) لحجم 640 | | النموذج | الحجم<br><sup>(بكسل) | دقة (أعلى 1)<br><sup>acc | دقة (أعلى 5)<br><sup>acc | سرعة التنفيذ<br><sup>ONNX للوحدة المركزية<br>(مللي ثانية) | سرعة التنفيذ<br><sup>A100 TensorRT<br>(مللي ثانية) | المعلمات<br><sup>(مليون) | FLOPs<br><sup>(مليار) لحجم 640 |
|----------------------------------------------------------------------------------------------|----------------------|--------------------------|--------------------------|-----------------------------------------------------------|----------------------------------------------------|--------------------------|--------------------------------| |----------------------------------------------------------------------------------------------|----------------------|--------------------------|--------------------------|-----------------------------------------------------------|----------------------------------------------------|--------------------------|--------------------------------|
| [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-cls.pt) | 224 | 66.6 | 87.0 | 12.9 | 0.31 | 2.7 | 4.3 | | [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-cls.pt) | 224 | 66.6 | 87.0 | 12.9 | 0.31 | 2.7 | 4.3 |
| [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-cls.pt) | 224 | 72.3 | 91.1 | 23.4 | 0.35 | 6.4 | 13.5 | | [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-cls.pt) | 224 | 72.3 | 91.1 | 23.4 | 0.35 | 6.4 | 13.5 |
| [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-cls.pt) | 224 | 76.4 | 93.2 | 85.4 | 0.62 | 17.0 | 42.7 | | [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-cls.pt) | 224 | 76.4 | 93.2 | 85.4 | 0.62 | 17.0 | 42.7 |
| [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-cls.pt) | 224 | 78.0 | 94.1 | 163.0 | 0.87 | 37.5 | 99.7 | | [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-cls.pt) | 224 | 78.0 | 94.1 | 163.0 | 0.87 | 37.5 | 99.7 |
| [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-cls.pt) | 224 | 78.4 | 94.3 | 232.0 | 1.01 | 57.4 | 154.8 | | [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-cls.pt) | 224 | 78.4 | 94.3 | 232.0 | 1.01 | 57.4 | 154.8 |
- قيمة **acc** هي دقة النماذج على مجموعة بيانات التحقق [ImageNet](https://www.image-net.org/). - قيمة **acc** هي دقة النماذج على مجموعة بيانات التحقق [ImageNet](https://www.image-net.org/).
<br>لإعادة إنتاج ذلك، استخدم `yolo val classify data=path/to/ImageNet device=0` <br>لإعادة إنتاج ذلك، استخدم `yolo val classify data=path/to/ImageNet device=0`

10
docs/ar/tasks/detect.md
View File

@ -35,11 +35,11 @@ Task التعرف على الكائنات هو عبارة عن تعرف على
| النموذج | الحجم<br><sup>(بكسل) | mAP<sup>val<br>50-95 | السرعة<br><sup>CPU ONNX<br>(مللي ثانية) | السرعة<br><sup>A100 TensorRT<br>(مللي ثانية) | الوزن<br><sup>(ميغا) | FLOPs<br><sup>(مليار) | | النموذج | الحجم<br><sup>(بكسل) | mAP<sup>val<br>50-95 | السرعة<br><sup>CPU ONNX<br>(مللي ثانية) | السرعة<br><sup>A100 TensorRT<br>(مللي ثانية) | الوزن<br><sup>(ميغا) | FLOPs<br><sup>(مليار) |
|--------------------------------------------------------------------------------------|----------------------|----------------------|-----------------------------------------|----------------------------------------------|----------------------|-----------------------| |--------------------------------------------------------------------------------------|----------------------|----------------------|-----------------------------------------|----------------------------------------------|----------------------|-----------------------|
| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 | | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 |
| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 | | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 |
| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 | | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 |
| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 | | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 |
| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 | | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 |
- قيم mAP<sup>val</sup> تنطبق على مقياس نموذج واحد-مقياس واحد على مجموعة بيانات [COCO val2017](http://cocodataset.org). - قيم mAP<sup>val</sup> تنطبق على مقياس نموذج واحد-مقياس واحد على مجموعة بيانات [COCO val2017](http://cocodataset.org).
<br>اعيد حسابها بواسطة `yolo val detect data=coco.yaml device=0` <br>اعيد حسابها بواسطة `yolo val detect data=coco.yaml device=0`

12
docs/ar/tasks/pose.md
View File

@ -33,12 +33,12 @@ keywords: Ultralytics، YOLO، YOLOv8، تقدير الوضعية ، كشف نق
| النموذج | الحجم (بالبكسل) | mAP<sup>الوضعية 50-95 | mAP<sup>الوضعية 50 | سرعة<sup>الوحدة المركزية ONNX<sup>(ms) | سرعة<sup>A100 TensorRT<sup>(ms) | المعلمات (مليون) | FLOPs (بالمليار) | | النموذج | الحجم (بالبكسل) | mAP<sup>الوضعية 50-95 | mAP<sup>الوضعية 50 | سرعة<sup>الوحدة المركزية ONNX<sup>(ms) | سرعة<sup>A100 TensorRT<sup>(ms) | المعلمات (مليون) | FLOPs (بالمليار) |
|------------------------------------------------------------------------------------------------------|-----------------|-----------------------|--------------------|----------------------------------------|---------------------------------|------------------|------------------| |------------------------------------------------------------------------------------------------------|-----------------|-----------------------|--------------------|----------------------------------------|---------------------------------|------------------|------------------|
| [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 | | [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 |
| [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 | | [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 |
| [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 | | [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 |
| [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 | | [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 |
| [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 | | [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 |
| [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 | | [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 |
- تعتبر القيم **mAP<sup>val</sup>** لنموذج واحد ومقياس واحد فقط على [COCO Keypoints val2017](http://cocodataset.org) - تعتبر القيم **mAP<sup>val</sup>** لنموذج واحد ومقياس واحد فقط على [COCO Keypoints val2017](http://cocodataset.org)
مجموعة البيانات. مجموعة البيانات.

10
docs/ar/tasks/segment.md
View File

@ -35,11 +35,11 @@ keywords: yolov8 ، فصل الأشكال الفردية ، Ultralytics ، مج
| النموذج | الحجم<br><sup>بكسل | mAP<sup>box<br>50-95 | mAP<sup>mask<br>50-95 | السرعة<br><sup>CPU ONNX<br>(مللي ثانية) | السرعة<br><sup>A100 TensorRT<br>(مللي ثانية) | المعلمات<br><sup>(مليون) | FLOPs<br><sup>(مليار) | | النموذج | الحجم<br><sup>بكسل | mAP<sup>box<br>50-95 | mAP<sup>mask<br>50-95 | السرعة<br><sup>CPU ONNX<br>(مللي ثانية) | السرعة<br><sup>A100 TensorRT<br>(مللي ثانية) | المعلمات<br><sup>(مليون) | FLOPs<br><sup>(مليار) |
|----------------------------------------------------------------------------------------------|--------------------|----------------------|-----------------------|-----------------------------------------|----------------------------------------------|--------------------------|-----------------------| |----------------------------------------------------------------------------------------------|--------------------|----------------------|-----------------------|-----------------------------------------|----------------------------------------------|--------------------------|-----------------------|
| [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 | | [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 |
| [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 | | [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 |
| [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 | | [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 |
| [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 | | [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 |
| [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 | | [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 |
- تُستخدم قيم **mAP<sup>val</sup>** لنموذج واحد وحجم واحد على مجموعة بيانات [COCO val2017](http://cocodataset.org). - تُستخدم قيم **mAP<sup>val</sup>** لنموذج واحد وحجم واحد على مجموعة بيانات [COCO val2017](http://cocodataset.org).
<br>يمكن إعادة إنتاجها باستخدام `yolo val segment data=coco.yaml device=0` <br>يمكن إعادة إنتاجها باستخدام `yolo val segment data=coco.yaml device=0`

6
docs/de/models/yolo-nas.md
View File

@ -92,9 +92,9 @@ Im Folgenden finden Sie eine detaillierte Übersicht über jedes Modell, einschl
| Modelltyp | Vortrainierte Gewichte | Unterstützte Aufgaben | Inferenz | Validierung | Training | Export | | Modelltyp | Vortrainierte Gewichte | Unterstützte Aufgaben | Inferenz | Validierung | Training | Export |
|------------|-----------------------------------------------------------------------------------------------|---------------------------------------|----------|-------------|----------|--------| |------------|-----------------------------------------------------------------------------------------------|---------------------------------------|----------|-------------|----------|--------|
| YOLO-NAS-s | [yolo_nas_s.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolo_nas_s.pt) | [Objekterkennung](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ | | YOLO-NAS-s | [yolo_nas_s.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolo_nas_s.pt) | [Objekterkennung](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ |
| YOLO-NAS-m | [yolo_nas_m.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolo_nas_m.pt) | [Objekterkennung](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ | | YOLO-NAS-m | [yolo_nas_m.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolo_nas_m.pt) | [Objekterkennung](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ |
| YOLO-NAS-l | [yolo_nas_l.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolo_nas_l.pt) | [Objekterkennung](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ | | YOLO-NAS-l | [yolo_nas_l.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolo_nas_l.pt) | [Objekterkennung](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ |
## Zitierungen und Danksagungen ## Zitierungen und Danksagungen

20
docs/de/models/yolov5.md
View File

@ -40,17 +40,17 @@ Diese Tabelle bietet eine detaillierte Übersicht über die verschiedenen Varian
| Modell | YAML | Größe<br><sup>(Pixel) | mAP<sup>val<br>50-95 | Geschwindigkeit<br><sup>CPU ONNX<br>(ms) | Geschwindigkeit<br><sup>A100 TensorRT<br>(ms) | Parameter<br><sup>(M) | FLOPs<br><sup>(B) | | Modell | YAML | Größe<br><sup>(Pixel) | mAP<sup>val<br>50-95 | Geschwindigkeit<br><sup>CPU ONNX<br>(ms) | Geschwindigkeit<br><sup>A100 TensorRT<br>(ms) | Parameter<br><sup>(M) | FLOPs<br><sup>(B) |
|---------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------|-----------------------|----------------------|------------------------------------------|-----------------------------------------------|--------------------|-------------------| |---------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------|-----------------------|----------------------|------------------------------------------|-----------------------------------------------|--------------------|-------------------|
| [yolov5nu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5nu.pt) | [yolov5n.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 34,3 | 73,6 | 1,06 | 2,6 | 7,7 | | [yolov5nu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5nu.pt) | [yolov5n.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 34,3 | 73,6 | 1,06 | 2,6 | 7,7 |
| [yolov5su.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5su.pt) | [yolov5s.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 43,0 | 120,7 | 1,27 | 9,1 | 24,0 | | [yolov5su.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5su.pt) | [yolov5s.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 43,0 | 120,7 | 1,27 | 9,1 | 24,0 |
| [yolov5mu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5mu.pt) | [yolov5m.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 49,0 | 233,9 | 1,86 | 25,1 | 64,2 | | [yolov5mu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5mu.pt) | [yolov5m.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 49,0 | 233,9 | 1,86 | 25,1 | 64,2 |
| [yolov5lu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5lu.pt) | [yolov5l.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 52,2 | 408,4 | 2,50 | 53,2 | 135,0 | | [yolov5lu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5lu.pt) | [yolov5l.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 52,2 | 408,4 | 2,50 | 53,2 | 135,0 |
| [yolov5xu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5xu.pt) | [yolov5x.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 53,2 | 763,2 | 3,81 | 97,2 | 246,4 | | [yolov5xu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5xu.pt) | [yolov5x.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 53,2 | 763,2 | 3,81 | 97,2 | 246,4 |
| | | | | | | | | | | | | | | | | |
| [yolov5n6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5n6u.pt) | [yolov5n6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1.280 | 42,1 | 211,0 | 1,83 | 4,3 | 7,8 | | [yolov5n6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5n6u.pt) | [yolov5n6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1.280 | 42,1 | 211,0 | 1,83 | 4,3 | 7,8 |
| [yolov5s6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5s6u.pt) | [yolov5s6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1.280 | 48,6 | 422,6 | 2,34 | 15,3 | 24,6 | | [yolov5s6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5s6u.pt) | [yolov5s6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1.280 | 48,6 | 422,6 | 2,34 | 15,3 | 24,6 |
| [yolov5m6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5m6u.pt) | [yolov5m6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1.280 | 53,6 | 810,9 | 4,36 | 41,2 | 65,7 | | [yolov5m6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5m6u.pt) | [yolov5m6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1.280 | 53,6 | 810,9 | 4,36 | 41,2 | 65,7 |
| [yolov5l6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5l6u.pt) | [yolov5l6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1.280 | 55,7 | 1.470,9 | 5,47 | 86,1 | 137,4 | | [yolov5l6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5l6u.pt) | [yolov5l6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1.280 | 55,7 | 1.470,9 | 5,47 | 86,1 | 137,4 |
| [yolov5x6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5x6u.pt) | [yolov5x6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1.280 | 56,8 | 2.436,5 | 8,98 | 155,4 | 250,7 | | [yolov5x6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5x6u.pt) | [yolov5x6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1.280 | 56,8 | 2.436,5 | 8,98 | 155,4 | 250,7 |
## Beispiele zur Verwendung ## Beispiele zur Verwendung

52
docs/de/models/yolov8.md
View File

@ -44,11 +44,11 @@ Diese Tabelle gibt einen Überblick über die verschiedenen Varianten des YOLOv8
| Modell | Größe<br><sup>(Pixel) | mAP<sup>val<br>50-95 | Geschwindigkeit<br><sup>CPU ONNX<br>(ms) | Geschwindigkeit<br><sup>A100 TensorRT<br>(ms) | Parameter<br><sup>(M) | FLOPs<br><sup>(B) | | Modell | Größe<br><sup>(Pixel) | mAP<sup>val<br>50-95 | Geschwindigkeit<br><sup>CPU ONNX<br>(ms) | Geschwindigkeit<br><sup>A100 TensorRT<br>(ms) | Parameter<br><sup>(M) | FLOPs<br><sup>(B) |
| ------------------------------------------------------------------------------------ | --------------------- | -------------------- | ---------------------------------------- | --------------------------------------------- | ------------------ | ----------------- | | ------------------------------------------------------------------------------------ | --------------------- | -------------------- | ---------------------------------------- | --------------------------------------------- | ------------------ | ----------------- |
| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt) | 640 | 37,3 | 80,4 | 0,99 | 3,2 | 8,7 | | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt) | 640 | 37,3 | 80,4 | 0,99 | 3,2 | 8,7 |
| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s.pt) | 640 | 44,9 | 128,4 | 1,20 | 11,2 | 28,6 | | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s.pt) | 640 | 44,9 | 128,4 | 1,20 | 11,2 | 28,6 |
| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m.pt) | 640 | 50,2 | 234,7 | 1,83 | 25,9 | 78,9 | | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m.pt) | 640 | 50,2 | 234,7 | 1,83 | 25,9 | 78,9 |
| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l.pt) | 640 | 52,9 | 375,2 | 2,39 | 43,7 | 165,2 | | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l.pt) | 640 | 52,9 | 375,2 | 2,39 | 43,7 | 165,2 |
| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x.pt) | 640 | 53,9 | 479,1 | 3,53 | 68,2 | 257,8 | | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x.pt) | 640 | 53,9 | 479,1 | 3,53 | 68,2 | 257,8 |
=== "Objekterkennung (Open Images V7)" === "Objekterkennung (Open Images V7)"
@ -56,11 +56,11 @@ Diese Tabelle gibt einen Überblick über die verschiedenen Varianten des YOLOv8
| Modell | Größe<br><sup>(Pixel) | mAP<sup>val<br>50-95 | Geschwindigkeit<br><sup>CPU ONNX<br>(ms) | Geschwindigkeit<br><sup>A100 TensorRT<br>(ms) | Parameter<br><sup>(M) | FLOPs<br><sup>(B) | | Modell | Größe<br><sup>(Pixel) | mAP<sup>val<br>50-95 | Geschwindigkeit<br><sup>CPU ONNX<br>(ms) | Geschwindigkeit<br><sup>A100 TensorRT<br>(ms) | Parameter<br><sup>(M) | FLOPs<br><sup>(B) |
| ----------------------------------------------------------------------------------------- | --------------------- | -------------------- | ---------------------------------------- | --------------------------------------------- | ------------------ | ----------------- | | ----------------------------------------------------------------------------------------- | --------------------- | -------------------- | ---------------------------------------- | --------------------------------------------- | ------------------ | ----------------- |
| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-oiv7.pt) | 640 | 18,4 | 142,4 | 1,21 | 3,5 | 10,5 | | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-oiv7.pt) | 640 | 18,4 | 142,4 | 1,21 | 3,5 | 10,5 |
| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-oiv7.pt) | 640 | 27,7 | 183,1 | 1,40 | 11,4 | 29,7 | | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-oiv7.pt) | 640 | 27,7 | 183,1 | 1,40 | 11,4 | 29,7 |
| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-oiv7.pt) | 640 | 33,6 | 408,5 | 2,26 | 26,2 | 80,6 | | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-oiv7.pt) | 640 | 33,6 | 408,5 | 2,26 | 26,2 | 80,6 |
| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-oiv7.pt) | 640 | 34,9 | 596,9 | 2,43 | 44,1 | 167,4 | | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-oiv7.pt) | 640 | 34,9 | 596,9 | 2,43 | 44,1 | 167,4 |
| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-oiv7.pt) | 640 | 36,3 | 860,6 | 3,56 | 68,7 | 260,6 | | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-oiv7.pt) | 640 | 36,3 | 860,6 | 3,56 | 68,7 | 260,6 |
=== "Segmentierung (COCO)" === "Segmentierung (COCO)"
@ -68,11 +68,11 @@ Diese Tabelle gibt einen Überblick über die verschiedenen Varianten des YOLOv8
| Modell | Größe<br><sup>(Pixel) | mAP<sup>box<br>50-95 | mAP<sup>mask<br>50-95 | Geschwindigkeit<br><sup>CPU ONNX<br>(ms) | Geschwindigkeit<br><sup>A100 TensorRT<br>(ms) | Parameter<br><sup>(M) | FLOPs<br><sup>(B) | | Modell | Größe<br><sup>(Pixel) | mAP<sup>box<br>50-95 | mAP<sup>mask<br>50-95 | Geschwindigkeit<br><sup>CPU ONNX<br>(ms) | Geschwindigkeit<br><sup>A100 TensorRT<br>(ms) | Parameter<br><sup>(M) | FLOPs<br><sup>(B) |
| -------------------------------------------------------------------------------------------- | --------------------- | --------------------- | --------------------- | ---------------------------------------- | --------------------------------------------- | ------------------ | ----------------- | | -------------------------------------------------------------------------------------------- | --------------------- | --------------------- | --------------------- | ---------------------------------------- | --------------------------------------------- | ------------------ | ----------------- |
| [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-seg.pt) | 640 | 36,7 | 30,5 | 96,1 | 1,21 | 3,4 | 12,6 | | [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-seg.pt) | 640 | 36,7 | 30,5 | 96,1 | 1,21 | 3,4 | 12,6 |
| [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-seg.pt) | 640 | 44,6 | 36,8 | 155,7 | 1,47 | 11,8 | 42,6 | | [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-seg.pt) | 640 | 44,6 | 36,8 | 155,7 | 1,47 | 11,8 | 42,6 |
| [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-seg.pt) | 640 | 49,9 | 40,8 | 317,0 | 2,18 | 27,3 | 110,2 | | [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-seg.pt) | 640 | 49,9 | 40,8 | 317,0 | 2,18 | 27,3 | 110,2 |
| [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-seg.pt) | 640 | 52,3 | 42,6 | 572,4 | 2,79 | 46,0 | 220,5 | | [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-seg.pt) | 640 | 52,3 | 42,6 | 572,4 | 2,79 | 46,0 | 220,5 |
| [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-seg.pt) | 640 | 53,4 | 43,4 | 712,1 | 4,02 | 71,8 | 344,1 | | [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-seg.pt) | 640 | 53,4 | 43,4 | 712,1 | 4,02 | 71,8 | 344,1 |
=== "Klassifikation (ImageNet)" === "Klassifikation (ImageNet)"
@ -80,11 +80,11 @@ Diese Tabelle gibt einen Überblick über die verschiedenen Varianten des YOLOv8
| Modell | Größe<br><sup>(Pixel) | acc<br><sup>top1 | acc<br><sup>top5 | Geschwindigkeit<br><sup>CPU ONNX<br>(ms) | Geschwindigkeit<br><sup>A100 TensorRT<br>(ms) | Parameter<br><sup>(M) | FLOPs<br><sup>(B) bei 640 | | Modell | Größe<br><sup>(Pixel) | acc<br><sup>top1 | acc<br><sup>top5 | Geschwindigkeit<br><sup>CPU ONNX<br>(ms) | Geschwindigkeit<br><sup>A100 TensorRT<br>(ms) | Parameter<br><sup>(M) | FLOPs<br><sup>(B) bei 640 |
| -------------------------------------------------------------------------------------------- | --------------------- | ---------------- | ---------------- | ---------------------------------------- | --------------------------------------------- | ------------------ | ------------------------ | | -------------------------------------------------------------------------------------------- | --------------------- | ---------------- | ---------------- | ---------------------------------------- | --------------------------------------------- | ------------------ | ------------------------ |
| [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-cls.pt) | 224 | 66,6 | 87,0 | 12,9 | 0,31 | 2,7 | 4,3 | | [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-cls.pt) | 224 | 66,6 | 87,0 | 12,9 | 0,31 | 2,7 | 4,3 |
| [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-cls.pt) | 224 | 72,3 | 91,1 | 23,4 | 0,35 | 6,4 | 13,5 | | [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-cls.pt) | 224 | 72,3 | 91,1 | 23,4 | 0,35 | 6,4 | 13,5 |
| [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-cls.pt) | 224 | 76,4 | 93,2 | 85,4 | 0,62 | 17,0 | 42,7 | | [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-cls.pt) | 224 | 76,4 | 93,2 | 85,4 | 0,62 | 17,0 | 42,7 |
| [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-cls.pt) | 224 | 78,0 | 94,1 | 163,0 | 0,87 | 37,5 | 99,7 | | [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-cls.pt) | 224 | 78,0 | 94,1 | 163,0 | 0,87 | 37,5 | 99,7 |
| [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-cls.pt) | 224 | 78,4 | 94,3 | 232,0 | 1,01 | 57,4 | 154,8 | | [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-cls.pt) | 224 | 78,4 | 94,3 | 232,0 | 1,01 | 57,4 | 154,8 |
=== "Pose (COCO)" === "Pose (COCO)"
@ -92,12 +92,12 @@ Diese Tabelle gibt einen Überblick über die verschiedenen Varianten des YOLOv8
| Modell | Größe<br><sup>(Pixel) | mAP<sup>pose<br>50-95 | mAP<sup>pose<br>50 | Geschwindigkeit<br><sup>CPU ONNX<br>(ms) | Geschwindigkeit<br><sup>A100 TensorRT<br>(ms) | Parameter<br><sup>(M) | FLOPs<br><sup>(B) | | Modell | Größe<br><sup>(Pixel) | mAP<sup>pose<br>50-95 | mAP<sup>pose<br>50 | Geschwindigkeit<br><sup>CPU ONNX<br>(ms) | Geschwindigkeit<br><sup>A100 TensorRT<br>(ms) | Parameter<br><sup>(M) | FLOPs<br><sup>(B) |
| ---------------------------------------------------------------------------------------------------- | --------------------- | --------------------- | ------------------ | ---------------------------------------- | --------------------------------------------- | ------------------ | ----------------- | | ---------------------------------------------------------------------------------------------------- | --------------------- | --------------------- | ------------------ | ---------------------------------------- | --------------------------------------------- | ------------------ | ----------------- |
| [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-pose.pt) | 640 | 50,4 | 80,1 | 131,8 | 1,18 | 3,3 | 9,2 | | [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-pose.pt) | 640 | 50,4 | 80,1 | 131,8 | 1,18 | 3,3 | 9,2 |
| [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-pose.pt) | 640 | 60,0 | 86,2 | 233,2 | 1,42 | 11,6 | 30,2 | | [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-pose.pt) | 640 | 60,0 | 86,2 | 233,2 | 1,42 | 11,6 | 30,2 |
| [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-pose.pt) | 640 | 65,0 | 88,8 | 456,3 | 2,00 | 26,4 | 81,0 | | [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-pose.pt) | 640 | 65,0 | 88,8 | 456,3 | 2,00 | 26,4 | 81,0 |
| [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-pose.pt) | 640 | 67,6 | 90,0 | 784,5 | 2,59 | 44,4 | 168,6 | | [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-pose.pt) | 640 | 67,6 | 90,0 | 784,5 | 2,59 | 44,4 | 168,6 |
| [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose.pt) | 640 | 69,2 | 90,2 | 1607,1 | 3,73 | 69,4 | 263,2 | | [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose.pt) | 640 | 69,2 | 90,2 | 1607,1 | 3,73 | 69,4 | 263,2 |
| [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose-p6.pt) | 1280 | 71,6 | 91,2 | 4088,7 | 10,04 | 99,1 | 1066,4 | | [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose-p6.pt) | 1280 | 71,6 | 91,2 | 4088,7 | 10,04 | 99,1 | 1066,4 |
## Beispiele zur Verwendung ## Beispiele zur Verwendung

10
docs/de/tasks/classify.md
View File

@ -24,11 +24,11 @@ Hier werden vortrainierte YOLOv8 Classify-Modelle gezeigt. Detect-, Segment- und
| Modell | Größe<br><sup>(Pixel) | Genauigkeit<br><sup>top1 | Genauigkeit<br><sup>top5 | Geschwindigkeit<br><sup>CPU ONNX<br>(ms) | Geschwindigkeit<br><sup>A100 TensorRT<br>(ms) | Parameter<br><sup>(M) | FLOPs<br><sup>(B) bei 640 | | Modell | Größe<br><sup>(Pixel) | Genauigkeit<br><sup>top1 | Genauigkeit<br><sup>top5 | Geschwindigkeit<br><sup>CPU ONNX<br>(ms) | Geschwindigkeit<br><sup>A100 TensorRT<br>(ms) | Parameter<br><sup>(M) | FLOPs<br><sup>(B) bei 640 |
|----------------------------------------------------------------------------------------------|-----------------------|--------------------------|--------------------------|------------------------------------------|-----------------------------------------------|-----------------------|---------------------------| |----------------------------------------------------------------------------------------------|-----------------------|--------------------------|--------------------------|------------------------------------------|-----------------------------------------------|-----------------------|---------------------------|
| [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-cls.pt) | 224 | 66.6 | 87.0 | 12.9 | 0.31 | 2.7 | 4.3 | | [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-cls.pt) | 224 | 66.6 | 87.0 | 12.9 | 0.31 | 2.7 | 4.3 |
| [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-cls.pt) | 224 | 72.3 | 91.1 | 23.4 | 0.35 | 6.4 | 13.5 | | [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-cls.pt) | 224 | 72.3 | 91.1 | 23.4 | 0.35 | 6.4 | 13.5 |
| [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-cls.pt) | 224 | 76.4 | 93.2 | 85.4 | 0.62 | 17.0 | 42.7 | | [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-cls.pt) | 224 | 76.4 | 93.2 | 85.4 | 0.62 | 17.0 | 42.7 |
| [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-cls.pt) | 224 | 78.0 | 94.1 | 163.0 | 0.87 | 37.5 | 99.7 | | [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-cls.pt) | 224 | 78.0 | 94.1 | 163.0 | 0.87 | 37.5 | 99.7 |
| [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-cls.pt) | 224 | 78.4 | 94.3 | 232.0 | 1.01 | 57.4 | 154.8 | | [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-cls.pt) | 224 | 78.4 | 94.3 | 232.0 | 1.01 | 57.4 | 154.8 |
- **Genauigkeit**-Werte sind Modellgenauigkeiten auf dem [ImageNet](https://www.image-net.org/)-Datensatz Validierungsset. - **Genauigkeit**-Werte sind Modellgenauigkeiten auf dem [ImageNet](https://www.image-net.org/)-Datensatz Validierungsset.
<br>Zur Reproduktion `yolo val classify data=pfad/zu/ImageNet device=0 verwenden` <br>Zur Reproduktion `yolo val classify data=pfad/zu/ImageNet device=0 verwenden`

10
docs/de/tasks/detect.md
View File

@ -35,11 +35,11 @@ Hier werden die vortrainierten YOLOv8 Detect Modelle gezeigt. Detect, Segment un
| Modell | Größe<br><sup>(Pixel) | mAP<sup>val<br>50-95 | Geschwindigkeit<br><sup>CPU ONNX<br>(ms) | Geschwindigkeit<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) | | Modell | Größe<br><sup>(Pixel) | mAP<sup>val<br>50-95 | Geschwindigkeit<br><sup>CPU ONNX<br>(ms) | Geschwindigkeit<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) |
|--------------------------------------------------------------------------------------|-----------------------|----------------------|------------------------------------------|-----------------------------------------------|--------------------|-------------------| |--------------------------------------------------------------------------------------|-----------------------|----------------------|------------------------------------------|-----------------------------------------------|--------------------|-------------------|
| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 | | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 |
| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 | | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 |
| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 | | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 |
| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 | | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 |
| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 | | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 |
- **mAP<sup>val</sup>** Werte sind für Single-Modell Single-Scale auf dem [COCO val2017](http://cocodataset.org) Datensatz. - **mAP<sup>val</sup>** Werte sind für Single-Modell Single-Scale auf dem [COCO val2017](http://cocodataset.org) Datensatz.
<br>Reproduzieren mit `yolo val detect data=coco.yaml device=0` <br>Reproduzieren mit `yolo val detect data=coco.yaml device=0`

12
docs/de/tasks/pose.md
View File

@ -35,12 +35,12 @@ Hier werden vortrainierte YOLOv8 Pose-Modelle gezeigt. Erkennungs-, Segmentierun
| Modell | Größe<br><sup>(Pixel) | mAP<sup>pose<br>50-95 | mAP<sup>pose<br>50 | Geschwindigkeit<br><sup>CPU ONNX<br>(ms) | Geschwindigkeit<br><sup>A100 TensorRT<br>(ms) | Parameter<br><sup>(M) | FLOPs<br><sup>(B) | | Modell | Größe<br><sup>(Pixel) | mAP<sup>pose<br>50-95 | mAP<sup>pose<br>50 | Geschwindigkeit<br><sup>CPU ONNX<br>(ms) | Geschwindigkeit<br><sup>A100 TensorRT<br>(ms) | Parameter<br><sup>(M) | FLOPs<br><sup>(B) |
|------------------------------------------------------------------------------------------------------|-----------------------|-----------------------|--------------------|------------------------------------------|-----------------------------------------------|-----------------------|-------------------| |------------------------------------------------------------------------------------------------------|-----------------------|-----------------------|--------------------|------------------------------------------|-----------------------------------------------|-----------------------|-------------------|
| [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-pose.pt) | 640 | 50,4 | 80,1 | 131,8 | 1,18 | 3,3 | 9,2 | | [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-pose.pt) | 640 | 50,4 | 80,1 | 131,8 | 1,18 | 3,3 | 9,2 |
| [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-pose.pt) | 640 | 60,0 | 86,2 | 233,2 | 1,42 | 11,6 | 30,2 | | [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-pose.pt) | 640 | 60,0 | 86,2 | 233,2 | 1,42 | 11,6 | 30,2 |
| [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-pose.pt) | 640 | 65,0 | 88,8 | 456,3 | 2,00 | 26,4 | 81,0 | | [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-pose.pt) | 640 | 65,0 | 88,8 | 456,3 | 2,00 | 26,4 | 81,0 |
| [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-pose.pt) | 640 | 67,6 | 90,0 | 784,5 | 2,59 | 44,4 | 168,6 | | [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-pose.pt) | 640 | 67,6 | 90,0 | 784,5 | 2,59 | 44,4 | 168,6 |
| [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose.pt) | 640 | 69,2 | 90,2 | 1607,1 | 3,73 | 69,4 | 263,2 | | [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose.pt) | 640 | 69,2 | 90,2 | 1607,1 | 3,73 | 69,4 | 263,2 |
| [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose-p6.pt) | 1280 | 71,6 | 91,2 | 4088,7 | 10,04 | 99,1 | 1066,4 | | [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose-p6.pt) | 1280 | 71,6 | 91,2 | 4088,7 | 10,04 | 99,1 | 1066,4 |
- **mAP<sup>val</sup>** Werte gelten für ein einzelnes Modell mit einfacher Skala auf dem [COCO Keypoints val2017](http://cocodataset.org)-Datensatz. - **mAP<sup>val</sup>** Werte gelten für ein einzelnes Modell mit einfacher Skala auf dem [COCO Keypoints val2017](http://cocodataset.org)-Datensatz.
<br>Zu reproduzieren mit `yolo val pose data=coco-pose.yaml device=0`. <br>Zu reproduzieren mit `yolo val pose data=coco-pose.yaml device=0`.

10
docs/de/tasks/segment.md
View File

@ -35,11 +35,11 @@ Hier werden vortrainierte YOLOv8 Segment-Modelle gezeigt. Detect-, Segment- und
| Modell | Größe<br><sup>(Pixel) | mAP<sup>Kasten<br>50-95 | mAP<sup>Masken<br>50-95 | Geschwindigkeit<br><sup>CPU ONNX<br>(ms) | Geschwindigkeit<br><sup>A100 TensorRT<br>(ms) | Parameter<br><sup>(M) | FLOPs<br><sup>(B) | | Modell | Größe<br><sup>(Pixel) | mAP<sup>Kasten<br>50-95 | mAP<sup>Masken<br>50-95 | Geschwindigkeit<br><sup>CPU ONNX<br>(ms) | Geschwindigkeit<br><sup>A100 TensorRT<br>(ms) | Parameter<br><sup>(M) | FLOPs<br><sup>(B) |
|----------------------------------------------------------------------------------------------|-----------------------|-------------------------|-------------------------|------------------------------------------|-----------------------------------------------|-----------------------|-------------------| |----------------------------------------------------------------------------------------------|-----------------------|-------------------------|-------------------------|------------------------------------------|-----------------------------------------------|-----------------------|-------------------|
| [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 | | [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 |
| [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 | | [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 |
| [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 | | [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 |
| [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 | | [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 |
| [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 | | [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 |
- Die **mAP<sup>val</sup>**-Werte sind für ein einzelnes Modell, einzelne Skala auf dem [COCO val2017](http://cocodataset.org)-Datensatz. - Die **mAP<sup>val</sup>**-Werte sind für ein einzelnes Modell, einzelne Skala auf dem [COCO val2017](http://cocodataset.org)-Datensatz.
<br>Zum Reproduzieren nutzen Sie `yolo val segment data=coco.yaml device=0` <br>Zum Reproduzieren nutzen Sie `yolo val segment data=coco.yaml device=0`

6
docs/en/models/yolo-nas.md
View File

@ -91,9 +91,9 @@ Below is a detailed overview of each model, including links to their pre-trained
| Model Type | Pre-trained Weights | Tasks Supported | Inference | Validation | Training | Export | | Model Type | Pre-trained Weights | Tasks Supported | Inference | Validation | Training | Export |
|------------|-----------------------------------------------------------------------------------------------|----------------------------------------|-----------|------------|----------|--------| |------------|-----------------------------------------------------------------------------------------------|----------------------------------------|-----------|------------|----------|--------|
| YOLO-NAS-s | [yolo_nas_s.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolo_nas_s.pt) | [Object Detection](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ | | YOLO-NAS-s | [yolo_nas_s.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolo_nas_s.pt) | [Object Detection](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ |
| YOLO-NAS-m | [yolo_nas_m.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolo_nas_m.pt) | [Object Detection](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ | | YOLO-NAS-m | [yolo_nas_m.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolo_nas_m.pt) | [Object Detection](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ |
| YOLO-NAS-l | [yolo_nas_l.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolo_nas_l.pt) | [Object Detection](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ | | YOLO-NAS-l | [yolo_nas_l.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolo_nas_l.pt) | [Object Detection](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ |
## Citations and Acknowledgements ## Citations and Acknowledgements

20
docs/en/models/yolov5.md
View File

@ -40,17 +40,17 @@ This table provides a detailed overview of the YOLOv5u model variants, highlight
| Model | YAML | size<br><sup>(pixels) | mAP<sup>val<br>50-95 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) | | Model | YAML | size<br><sup>(pixels) | mAP<sup>val<br>50-95 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) |
|---------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------|-----------------------|----------------------|--------------------------------|-------------------------------------|--------------------|-------------------| |---------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------|-----------------------|----------------------|--------------------------------|-------------------------------------|--------------------|-------------------|
| [yolov5nu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5nu.pt) | [yolov5n.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 34.3 | 73.6 | 1.06 | 2.6 | 7.7 | | [yolov5nu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5nu.pt) | [yolov5n.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 34.3 | 73.6 | 1.06 | 2.6 | 7.7 |
| [yolov5su.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5su.pt) | [yolov5s.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 43.0 | 120.7 | 1.27 | 9.1 | 24.0 | | [yolov5su.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5su.pt) | [yolov5s.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 43.0 | 120.7 | 1.27 | 9.1 | 24.0 |
| [yolov5mu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5mu.pt) | [yolov5m.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 49.0 | 233.9 | 1.86 | 25.1 | 64.2 | | [yolov5mu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5mu.pt) | [yolov5m.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 49.0 | 233.9 | 1.86 | 25.1 | 64.2 |
| [yolov5lu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5lu.pt) | [yolov5l.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 52.2 | 408.4 | 2.50 | 53.2 | 135.0 | | [yolov5lu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5lu.pt) | [yolov5l.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 52.2 | 408.4 | 2.50 | 53.2 | 135.0 |
| [yolov5xu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5xu.pt) | [yolov5x.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 53.2 | 763.2 | 3.81 | 97.2 | 246.4 | | [yolov5xu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5xu.pt) | [yolov5x.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 53.2 | 763.2 | 3.81 | 97.2 | 246.4 |
| | | | | | | | | | | | | | | | | |
| [yolov5n6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5n6u.pt) | [yolov5n6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 42.1 | 211.0 | 1.83 | 4.3 | 7.8 | | [yolov5n6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5n6u.pt) | [yolov5n6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 42.1 | 211.0 | 1.83 | 4.3 | 7.8 |
| [yolov5s6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5s6u.pt) | [yolov5s6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 48.6 | 422.6 | 2.34 | 15.3 | 24.6 | | [yolov5s6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5s6u.pt) | [yolov5s6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 48.6 | 422.6 | 2.34 | 15.3 | 24.6 |
| [yolov5m6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5m6u.pt) | [yolov5m6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 53.6 | 810.9 | 4.36 | 41.2 | 65.7 | | [yolov5m6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5m6u.pt) | [yolov5m6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 53.6 | 810.9 | 4.36 | 41.2 | 65.7 |
| [yolov5l6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5l6u.pt) | [yolov5l6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 55.7 | 1470.9 | 5.47 | 86.1 | 137.4 | | [yolov5l6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5l6u.pt) | [yolov5l6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 55.7 | 1470.9 | 5.47 | 86.1 | 137.4 |
| [yolov5x6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5x6u.pt) | [yolov5x6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 56.8 | 2436.5 | 8.98 | 155.4 | 250.7 | | [yolov5x6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5x6u.pt) | [yolov5x6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 56.8 | 2436.5 | 8.98 | 155.4 | 250.7 |
## Usage Examples ## Usage Examples

62
docs/en/models/yolov8.md
View File

@ -56,11 +56,11 @@ This table provides an overview of the YOLOv8 model variants, highlighting their
| Model | size<br><sup>(pixels) | mAP<sup>val<br>50-95 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) | | Model | size<br><sup>(pixels) | mAP<sup>val<br>50-95 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) |
| ------------------------------------------------------------------------------------ | --------------------- | -------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- | | ------------------------------------------------------------------------------------ | --------------------- | -------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 | | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 |
| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 | | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 |
| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 | | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 |
| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 | | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 |
| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 | | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 |
=== "Detection (Open Images V7)" === "Detection (Open Images V7)"
@ -68,11 +68,11 @@ This table provides an overview of the YOLOv8 model variants, highlighting their
| Model | size<br><sup>(pixels) | mAP<sup>val<br>50-95 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) | | Model | size<br><sup>(pixels) | mAP<sup>val<br>50-95 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) |
| ----------------------------------------------------------------------------------------- | --------------------- | -------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- | | ----------------------------------------------------------------------------------------- | --------------------- | -------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-oiv7.pt) | 640 | 18.4 | 142.4 | 1.21 | 3.5 | 10.5 | | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-oiv7.pt) | 640 | 18.4 | 142.4 | 1.21 | 3.5 | 10.5 |
| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-oiv7.pt) | 640 | 27.7 | 183.1 | 1.40 | 11.4 | 29.7 | | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-oiv7.pt) | 640 | 27.7 | 183.1 | 1.40 | 11.4 | 29.7 |
| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-oiv7.pt) | 640 | 33.6 | 408.5 | 2.26 | 26.2 | 80.6 | | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-oiv7.pt) | 640 | 33.6 | 408.5 | 2.26 | 26.2 | 80.6 |
| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-oiv7.pt) | 640 | 34.9 | 596.9 | 2.43 | 44.1 | 167.4 | | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-oiv7.pt) | 640 | 34.9 | 596.9 | 2.43 | 44.1 | 167.4 |
| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-oiv7.pt) | 640 | 36.3 | 860.6 | 3.56 | 68.7 | 260.6 | | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-oiv7.pt) | 640 | 36.3 | 860.6 | 3.56 | 68.7 | 260.6 |
=== "Segmentation (COCO)" === "Segmentation (COCO)"
@ -80,11 +80,11 @@ This table provides an overview of the YOLOv8 model variants, highlighting their
| Model | size<br><sup>(pixels) | mAP<sup>box<br>50-95 | mAP<sup>mask<br>50-95 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) | | Model | size<br><sup>(pixels) | mAP<sup>box<br>50-95 | mAP<sup>mask<br>50-95 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) |
| -------------------------------------------------------------------------------------------- | --------------------- | -------------------- | --------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- | | -------------------------------------------------------------------------------------------- | --------------------- | -------------------- | --------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
| [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 | | [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 |
| [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 | | [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 |
| [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 | | [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 |
| [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 | | [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 |
| [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 | | [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 |
=== "Classification (ImageNet)" === "Classification (ImageNet)"
@ -92,11 +92,11 @@ This table provides an overview of the YOLOv8 model variants, highlighting their
| Model | size<br><sup>(pixels) | acc<br><sup>top1 | acc<br><sup>top5 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) at 640 | | Model | size<br><sup>(pixels) | acc<br><sup>top1 | acc<br><sup>top5 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) at 640 |
| -------------------------------------------------------------------------------------------- | --------------------- | ---------------- | ---------------- | ------------------------------ | ----------------------------------- | ------------------ | ------------------------ | | -------------------------------------------------------------------------------------------- | --------------------- | ---------------- | ---------------- | ------------------------------ | ----------------------------------- | ------------------ | ------------------------ |
| [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-cls.pt) | 224 | 69.0 | 88.3 | 12.9 | 0.31 | 2.7 | 4.3 | | [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-cls.pt) | 224 | 69.0 | 88.3 | 12.9 | 0.31 | 2.7 | 4.3 |
| [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-cls.pt) | 224 | 73.8 | 91.7 | 23.4 | 0.35 | 6.4 | 13.5 | | [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-cls.pt) | 224 | 73.8 | 91.7 | 23.4 | 0.35 | 6.4 | 13.5 |
| [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-cls.pt) | 224 | 76.8 | 93.5 | 85.4 | 0.62 | 17.0 | 42.7 | | [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-cls.pt) | 224 | 76.8 | 93.5 | 85.4 | 0.62 | 17.0 | 42.7 |
| [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-cls.pt) | 224 | 76.8 | 93.5 | 163.0 | 0.87 | 37.5 | 99.7 | | [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-cls.pt) | 224 | 76.8 | 93.5 | 163.0 | 0.87 | 37.5 | 99.7 |
| [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-cls.pt) | 224 | 79.0 | 94.6 | 232.0 | 1.01 | 57.4 | 154.8 | | [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-cls.pt) | 224 | 79.0 | 94.6 | 232.0 | 1.01 | 57.4 | 154.8 |
=== "Pose (COCO)" === "Pose (COCO)"
@ -104,12 +104,12 @@ This table provides an overview of the YOLOv8 model variants, highlighting their
| Model | size<br><sup>(pixels) | mAP<sup>pose<br>50-95 | mAP<sup>pose<br>50 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) | | Model | size<br><sup>(pixels) | mAP<sup>pose<br>50-95 | mAP<sup>pose<br>50 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) |
| ---------------------------------------------------------------------------------------------------- | --------------------- | --------------------- | ------------------ | ------------------------------ | ----------------------------------- | ------------------ | ----------------- | | ---------------------------------------------------------------------------------------------------- | --------------------- | --------------------- | ------------------ | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
| [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 | | [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 |
| [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 | | [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 |
| [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 | | [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 |
| [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 | | [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 |
| [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 | | [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 |
| [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 | | [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 |
=== "OBB (DOTAv1)" === "OBB (DOTAv1)"
@ -117,11 +117,11 @@ This table provides an overview of the YOLOv8 model variants, highlighting their
| Model | size<br><sup>(pixels) | mAP<sup>test<br>50 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) | | Model | size<br><sup>(pixels) | mAP<sup>test<br>50 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) |
|----------------------------------------------------------------------------------------------|-----------------------| -------------------- | -------------------------------- | ------------------------------------- | -------------------- | ----------------- | |----------------------------------------------------------------------------------------------|-----------------------| -------------------- | -------------------------------- | ------------------------------------- | -------------------- | ----------------- |
| [YOLOv8n-obb](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-obb.pt) | 1024 | 76.9 | 204.77 | 3.57 | 3.1 | 23.3 | | [YOLOv8n-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-obb.pt) | 1024 | 76.9 | 204.77 | 3.57 | 3.1 | 23.3 |
| [YOLOv8s-obb](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-obb.pt) | 1024 | 78.0 | 424.88 | 4.07 | 11.4 | 76.3 | | [YOLOv8s-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-obb.pt) | 1024 | 78.0 | 424.88 | 4.07 | 11.4 | 76.3 |
| [YOLOv8m-obb](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-obb.pt) | 1024 | 80.5 | 763.48 | 7.61 | 26.4 | 208.6 | | [YOLOv8m-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-obb.pt) | 1024 | 80.5 | 763.48 | 7.61 | 26.4 | 208.6 |
| [YOLOv8l-obb](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-obb.pt) | 1024 | 80.7 | 1278.42 | 11.83 | 44.5 | 433.8 | | [YOLOv8l-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-obb.pt) | 1024 | 80.7 | 1278.42 | 11.83 | 44.5 | 433.8 |
| [YOLOv8x-obb](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-obb.pt) | 1024 | 81.36 | 1759.10 | 13.23 | 69.5 | 676.7 | | [YOLOv8x-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-obb.pt) | 1024 | 81.36 | 1759.10 | 13.23 | 69.5 | 676.7 |
## Usage Examples ## Usage Examples

10
docs/en/tasks/classify.md
View File

@ -35,11 +35,11 @@ YOLOv8 pretrained Classify models are shown here. Detect, Segment and Pose model
| Model | size<br><sup>(pixels) | acc<br><sup>top1 | acc<br><sup>top5 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) at 640 | | Model | size<br><sup>(pixels) | acc<br><sup>top1 | acc<br><sup>top5 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) at 640 |
|----------------------------------------------------------------------------------------------|-----------------------|------------------|------------------|--------------------------------|-------------------------------------|--------------------|--------------------------| |----------------------------------------------------------------------------------------------|-----------------------|------------------|------------------|--------------------------------|-------------------------------------|--------------------|--------------------------|
| [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-cls.pt) | 224 | 69.0 | 88.3 | 12.9 | 0.31 | 2.7 | 4.3 | | [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-cls.pt) | 224 | 69.0 | 88.3 | 12.9 | 0.31 | 2.7 | 4.3 |
| [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-cls.pt) | 224 | 73.8 | 91.7 | 23.4 | 0.35 | 6.4 | 13.5 | | [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-cls.pt) | 224 | 73.8 | 91.7 | 23.4 | 0.35 | 6.4 | 13.5 |
| [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-cls.pt) | 224 | 76.8 | 93.5 | 85.4 | 0.62 | 17.0 | 42.7 | | [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-cls.pt) | 224 | 76.8 | 93.5 | 85.4 | 0.62 | 17.0 | 42.7 |
| [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-cls.pt) | 224 | 76.8 | 93.5 | 163.0 | 0.87 | 37.5 | 99.7 | | [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-cls.pt) | 224 | 76.8 | 93.5 | 163.0 | 0.87 | 37.5 | 99.7 |
| [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-cls.pt) | 224 | 79.0 | 94.6 | 232.0 | 1.01 | 57.4 | 154.8 | | [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-cls.pt) | 224 | 79.0 | 94.6 | 232.0 | 1.01 | 57.4 | 154.8 |
- **acc** values are model accuracies on the [ImageNet](https://www.image-net.org/) dataset validation set. <br>Reproduce by `yolo val classify data=path/to/ImageNet device=0` - **acc** values are model accuracies on the [ImageNet](https://www.image-net.org/) dataset validation set. <br>Reproduce by `yolo val classify data=path/to/ImageNet device=0`
- **Speed** averaged over ImageNet val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val classify data=path/to/ImageNet batch=1 device=0|cpu` - **Speed** averaged over ImageNet val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val classify data=path/to/ImageNet batch=1 device=0|cpu`

10
docs/en/tasks/detect.md
View File

@ -35,11 +35,11 @@ YOLOv8 pretrained Detect models are shown here. Detect, Segment and Pose models
| Model | size<br><sup>(pixels) | mAP<sup>val<br>50-95 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) | | Model | size<br><sup>(pixels) | mAP<sup>val<br>50-95 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) |
|--------------------------------------------------------------------------------------|-----------------------|----------------------|--------------------------------|-------------------------------------|--------------------|-------------------| |--------------------------------------------------------------------------------------|-----------------------|----------------------|--------------------------------|-------------------------------------|--------------------|-------------------|
| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 | | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 |
| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 | | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 |
| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 | | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 |
| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 | | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 |
| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 | | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 |
- **mAP<sup>val</sup>** values are for single-model single-scale on [COCO val2017](http://cocodataset.org) dataset. <br>Reproduce by `yolo val detect data=coco.yaml device=0` - **mAP<sup>val</sup>** values are for single-model single-scale on [COCO val2017](http://cocodataset.org) dataset. <br>Reproduce by `yolo val detect data=coco.yaml device=0`
- **Speed** averaged over COCO val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val detect data=coco128.yaml batch=1 device=0|cpu` - **Speed** averaged over COCO val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val detect data=coco128.yaml batch=1 device=0|cpu`

10
docs/en/tasks/obb.md
View File

@ -26,11 +26,11 @@ YOLOv8 pretrained OBB models are shown here, which are pretrained on the [DOTAv1
| Model | size<br><sup>(pixels) | mAP<sup>test<br>50 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) | | Model | size<br><sup>(pixels) | mAP<sup>test<br>50 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) |
|----------------------------------------------------------------------------------------------|-----------------------| -------------------- | -------------------------------- | ------------------------------------- | -------------------- | ----------------- | |----------------------------------------------------------------------------------------------|-----------------------| -------------------- | -------------------------------- | ------------------------------------- | -------------------- | ----------------- |
| [YOLOv8n-obb](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-obb.pt) | 1024 | 76.9 | 204.77 | 3.57 | 3.1 | 23.3 | | [YOLOv8n-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-obb.pt) | 1024 | 76.9 | 204.77 | 3.57 | 3.1 | 23.3 |
| [YOLOv8s-obb](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-obb.pt) | 1024 | 78.0 | 424.88 | 4.07 | 11.4 | 76.3 | | [YOLOv8s-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-obb.pt) | 1024 | 78.0 | 424.88 | 4.07 | 11.4 | 76.3 |
| [YOLOv8m-obb](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-obb.pt) | 1024 | 80.5 | 763.48 | 7.61 | 26.4 | 208.6 | | [YOLOv8m-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-obb.pt) | 1024 | 80.5 | 763.48 | 7.61 | 26.4 | 208.6 |
| [YOLOv8l-obb](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-obb.pt) | 1024 | 80.7 | 1278.42 | 11.83 | 44.5 | 433.8 | | [YOLOv8l-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-obb.pt) | 1024 | 80.7 | 1278.42 | 11.83 | 44.5 | 433.8 |
| [YOLOv8x-obb](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-obb.pt) | 1024 | 81.36 | 1759.10 | 13.23 | 69.5 | 676.7 | | [YOLOv8x-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-obb.pt) | 1024 | 81.36 | 1759.10 | 13.23 | 69.5 | 676.7 |
- **mAP<sup>test</sup>** values are for single-model multi-scale on [DOTAv1 test](https://captain-whu.github.io/DOTA/index.html) dataset. <br>Reproduce by `yolo val obb data=DOTAv1.yaml device=0 split=test` and submit merged results to [DOTA evaluation](https://captain-whu.github.io/DOTA/evaluation.html). - **mAP<sup>test</sup>** values are for single-model multi-scale on [DOTAv1 test](https://captain-whu.github.io/DOTA/index.html) dataset. <br>Reproduce by `yolo val obb data=DOTAv1.yaml device=0 split=test` and submit merged results to [DOTA evaluation](https://captain-whu.github.io/DOTA/evaluation.html).
- **Speed** averaged over DOTAv1 val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val obb data=DOTAv1.yaml batch=1 device=0|cpu` - **Speed** averaged over DOTAv1 val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val obb data=DOTAv1.yaml batch=1 device=0|cpu`

12
docs/en/tasks/pose.md
View File

@ -35,12 +35,12 @@ YOLOv8 pretrained Pose models are shown here. Detect, Segment and Pose models ar
| Model | size<br><sup>(pixels) | mAP<sup>pose<br>50-95 | mAP<sup>pose<br>50 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) | | Model | size<br><sup>(pixels) | mAP<sup>pose<br>50-95 | mAP<sup>pose<br>50 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) |
|------------------------------------------------------------------------------------------------------|-----------------------|-----------------------|--------------------|--------------------------------|-------------------------------------|--------------------|-------------------| |------------------------------------------------------------------------------------------------------|-----------------------|-----------------------|--------------------|--------------------------------|-------------------------------------|--------------------|-------------------|
| [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 | | [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 |
| [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 | | [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 |
| [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 | | [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 |
| [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 | | [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 |
| [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 | | [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 |
| [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 | | [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 |
- **mAP<sup>val</sup>** values are for single-model single-scale on [COCO Keypoints val2017](http://cocodataset.org) dataset. <br>Reproduce by `yolo val pose data=coco-pose.yaml device=0` - **mAP<sup>val</sup>** values are for single-model single-scale on [COCO Keypoints val2017](http://cocodataset.org) dataset. <br>Reproduce by `yolo val pose data=coco-pose.yaml device=0`
- **Speed** averaged over COCO val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val pose data=coco8-pose.yaml batch=1 device=0|cpu` - **Speed** averaged over COCO val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val pose data=coco8-pose.yaml batch=1 device=0|cpu`

10
docs/en/tasks/segment.md
View File

@ -35,11 +35,11 @@ YOLOv8 pretrained Segment models are shown here. Detect, Segment and Pose models
| Model | size<br><sup>(pixels) | mAP<sup>box<br>50-95 | mAP<sup>mask<br>50-95 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) | | Model | size<br><sup>(pixels) | mAP<sup>box<br>50-95 | mAP<sup>mask<br>50-95 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) |
|----------------------------------------------------------------------------------------------|-----------------------|----------------------|-----------------------|--------------------------------|-------------------------------------|--------------------|-------------------| |----------------------------------------------------------------------------------------------|-----------------------|----------------------|-----------------------|--------------------------------|-------------------------------------|--------------------|-------------------|
| [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 | | [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 |
| [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 | | [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 |
| [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 | | [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 |
| [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 | | [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 |
| [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 | | [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 |
- **mAP<sup>val</sup>** values are for single-model single-scale on [COCO val2017](http://cocodataset.org) dataset. <br>Reproduce by `yolo val segment data=coco.yaml device=0` - **mAP<sup>val</sup>** values are for single-model single-scale on [COCO val2017](http://cocodataset.org) dataset. <br>Reproduce by `yolo val segment data=coco.yaml device=0`
- **Speed** averaged over COCO val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val segment data=coco128-seg.yaml batch=1 device=0|cpu` - **Speed** averaged over COCO val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val segment data=coco128-seg.yaml batch=1 device=0|cpu`

6
docs/es/models/yolo-nas.md
View File

@ -92,9 +92,9 @@ A continuación se muestra una descripción detallada de cada modelo, incluyendo
| Tipo de modelo | Pesos pre-entrenados | Tareas admitidas | Inferencia | Validación | Entrenamiento | Exportación | | Tipo de modelo | Pesos pre-entrenados | Tareas admitidas | Inferencia | Validación | Entrenamiento | Exportación |
|----------------|-----------------------------------------------------------------------------------------------|--------------------------------------------|------------|------------|---------------|-------------| |----------------|-----------------------------------------------------------------------------------------------|--------------------------------------------|------------|------------|---------------|-------------|
| YOLO-NAS-s | [yolo_nas_s.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolo_nas_s.pt) | [Detección de objetos](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ | | YOLO-NAS-s | [yolo_nas_s.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolo_nas_s.pt) | [Detección de objetos](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ |
| YOLO-NAS-m | [yolo_nas_m.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolo_nas_m.pt) | [Detección de objetos](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ | | YOLO-NAS-m | [yolo_nas_m.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolo_nas_m.pt) | [Detección de objetos](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ |
| YOLO-NAS-l | [yolo_nas_l.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolo_nas_l.pt) | [Detección de objetos](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ | | YOLO-NAS-l | [yolo_nas_l.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolo_nas_l.pt) | [Detección de objetos](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ |
## Citaciones y agradecimientos ## Citaciones y agradecimientos

20
docs/es/models/yolov5.md
View File

@ -40,17 +40,17 @@ Esta tabla proporciona una descripción detallada de las variantes de modelos YO
| Modelo | YAML | tamaño<br><sup>(píxeles) | mAP<sup>val<br>50-95 | Velocidad<br><sup>CPU ONNX<br>(ms) | Velocidad<br><sup>A100 TensorRT<br>(ms) | parámetros<br><sup>(M) | FLOPs<br><sup>(B) | | Modelo | YAML | tamaño<br><sup>(píxeles) | mAP<sup>val<br>50-95 | Velocidad<br><sup>CPU ONNX<br>(ms) | Velocidad<br><sup>A100 TensorRT<br>(ms) | parámetros<br><sup>(M) | FLOPs<br><sup>(B) |
|---------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------|-----------------------|----------------------|--------------------------------|-------------------------------------|--------------------|-------------------| |---------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------|-----------------------|----------------------|--------------------------------|-------------------------------------|--------------------|-------------------|
| [yolov5nu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5nu.pt) | [yolov5n.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 34.3 | 73.6 | 1.06 | 2.6 | 7.7 | | [yolov5nu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5nu.pt) | [yolov5n.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 34.3 | 73.6 | 1.06 | 2.6 | 7.7 |
| [yolov5su.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5su.pt) | [yolov5s.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 43.0 | 120.7 | 1.27 | 9.1 | 24.0 | | [yolov5su.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5su.pt) | [yolov5s.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 43.0 | 120.7 | 1.27 | 9.1 | 24.0 |
| [yolov5mu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5mu.pt) | [yolov5m.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 49.0 | 233.9 | 1.86 | 25.1 | 64.2 | | [yolov5mu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5mu.pt) | [yolov5m.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 49.0 | 233.9 | 1.86 | 25.1 | 64.2 |
| [yolov5lu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5lu.pt) | [yolov5l.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 52.2 | 408.4 | 2.50 | 53.2 | 135.0 | | [yolov5lu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5lu.pt) | [yolov5l.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 52.2 | 408.4 | 2.50 | 53.2 | 135.0 |
| [yolov5xu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5xu.pt) | [yolov5x.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 53.2 | 763.2 | 3.81 | 97.2 | 246.4 | | [yolov5xu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5xu.pt) | [yolov5x.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 53.2 | 763.2 | 3.81 | 97.2 | 246.4 |
| | | | | | | | | | | | | | | | | |
| [yolov5n6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5n6u.pt) | [yolov5n6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 42.1 | 211.0 | 1.83 | 4.3 | 7.8 | | [yolov5n6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5n6u.pt) | [yolov5n6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 42.1 | 211.0 | 1.83 | 4.3 | 7.8 |
| [yolov5s6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5s6u.pt) | [yolov5s6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 48.6 | 422.6 | 2.34 | 15.3 | 24.6 | | [yolov5s6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5s6u.pt) | [yolov5s6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 48.6 | 422.6 | 2.34 | 15.3 | 24.6 |
| [yolov5m6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5m6u.pt) | [yolov5m6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 53.6 | 810.9 | 4.36 | 41.2 | 65.7 | | [yolov5m6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5m6u.pt) | [yolov5m6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 53.6 | 810.9 | 4.36 | 41.2 | 65.7 |
| [yolov5l6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5l6u.pt) | [yolov5l6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 55.7 | 1470.9 | 5.47 | 86.1 | 137.4 | | [yolov5l6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5l6u.pt) | [yolov5l6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 55.7 | 1470.9 | 5.47 | 86.1 | 137.4 |
| [yolov5x6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5x6u.pt) | [yolov5x6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 56.8 | 2436.5 | 8.98 | 155.4 | 250.7 | | [yolov5x6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5x6u.pt) | [yolov5x6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 56.8 | 2436.5 | 8.98 | 155.4 | 250.7 |
## Ejemplos de Uso ## Ejemplos de Uso

52
docs/es/models/yolov8.md
View File

@ -44,11 +44,11 @@ Esta tabla proporciona una descripción general de las variantes de modelos YOLO
| Modelo | tamaño<br><sup>(píxeles) | mAP<sup>val<br>50-95 | Velocidad<br><sup>CPU ONNX<br>(ms) | Velocidad<br><sup>A100 TensorRT<br>(ms) | parámetros<br><sup>(M) | FLOPs<br><sup>(B) | | Modelo | tamaño<br><sup>(píxeles) | mAP<sup>val<br>50-95 | Velocidad<br><sup>CPU ONNX<br>(ms) | Velocidad<br><sup>A100 TensorRT<br>(ms) | parámetros<br><sup>(M) | FLOPs<br><sup>(B) |
| ------------------------------------------------------------------------------------ | ----------------------- | --------------------- | ------------------------------ | --------------------------------------- | ---------------------- | ----------------- | | ------------------------------------------------------------------------------------ | ----------------------- | --------------------- | ------------------------------ | --------------------------------------- | ---------------------- | ----------------- |
| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 | | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 |
| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 | | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 |
| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 | | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 |
| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 | | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 |
| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 | | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 |
=== "Detección (Open Images V7)" === "Detección (Open Images V7)"
@ -56,11 +56,11 @@ Esta tabla proporciona una descripción general de las variantes de modelos YOLO
| Modelo | tamaño<br><sup>(píxeles) | mAP<sup>val<br>50-95 | Velocidad<br><sup>CPU ONNX<br>(ms) | Velocidad<br><sup>A100 TensorRT<br>(ms) | parámetros<br><sup>(M) | FLOPs<br><sup>(B) | | Modelo | tamaño<br><sup>(píxeles) | mAP<sup>val<br>50-95 | Velocidad<br><sup>CPU ONNX<br>(ms) | Velocidad<br><sup>A100 TensorRT<br>(ms) | parámetros<br><sup>(M) | FLOPs<br><sup>(B) |
| ----------------------------------------------------------------------------------------- | ----------------------- | --------------------- | -------------------------------- | --------------------------------------- | ---------------------- | ----------------- | | ----------------------------------------------------------------------------------------- | ----------------------- | --------------------- | -------------------------------- | --------------------------------------- | ---------------------- | ----------------- |
| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-oiv7.pt) | 640 | 18.4 | 142.4 | 1.21 | 3.5 | 10.5 | | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-oiv7.pt) | 640 | 18.4 | 142.4 | 1.21 | 3.5 | 10.5 |
| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-oiv7.pt) | 640 | 27.7 | 183.1 | 1.40 | 11.4 | 29.7 | | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-oiv7.pt) | 640 | 27.7 | 183.1 | 1.40 | 11.4 | 29.7 |
| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-oiv7.pt) | 640 | 33.6 | 408.5 | 2.26 | 26.2 | 80.6 | | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-oiv7.pt) | 640 | 33.6 | 408.5 | 2.26 | 26.2 | 80.6 |
| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-oiv7.pt) | 640 | 34.9 | 596.9 | 2.43 | 44.1 | 167.4 | | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-oiv7.pt) | 640 | 34.9 | 596.9 | 2.43 | 44.1 | 167.4 |
| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-oiv7.pt) | 640 | 36.3 | 860.6 | 3.56 | 68.7 | 260.6 | | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-oiv7.pt) | 640 | 36.3 | 860.6 | 3.56 | 68.7 | 260.6 |
=== "Segmentación (COCO)" === "Segmentación (COCO)"
@ -68,11 +68,11 @@ Esta tabla proporciona una descripción general de las variantes de modelos YOLO
| Modelo | tamaño<br><sup>(píxeles) | mAP<sup>caja<br>50-95 | mAP<sup>máscara<br>50-95 | Velocidad<br><sup>CPU ONNX<br>(ms) | Velocidad<br><sup>A100 TensorRT<br>(ms) | parámetros<br><sup>(M) | FLOPs<br><sup>(B) | | Modelo | tamaño<br><sup>(píxeles) | mAP<sup>caja<br>50-95 | mAP<sup>máscara<br>50-95 | Velocidad<br><sup>CPU ONNX<br>(ms) | Velocidad<br><sup>A100 TensorRT<br>(ms) | parámetros<br><sup>(M) | FLOPs<br><sup>(B) |
| -------------------------------------------------------------------------------------------- | ----------------------- | ---------------------- | ----------------------- | -------------------------------- | --------------------------------------- | ---------------------- | ----------------- | | -------------------------------------------------------------------------------------------- | ----------------------- | ---------------------- | ----------------------- | -------------------------------- | --------------------------------------- | ---------------------- | ----------------- |
| [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 | | [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 |
| [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 | | [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 |
| [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 | | [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 |
| [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 | | [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 |
| [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 | | [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 |
=== "Clasificación (ImageNet)" === "Clasificación (ImageNet)"
@ -80,11 +80,11 @@ Esta tabla proporciona una descripción general de las variantes de modelos YOLO
| Modelo | tamaño<br><sup>(píxeles) | acc<br><sup>top1 | acc<br><sup>top5 | Velocidad<br><sup>CPU ONNX<br>(ms) | Velocidad<br><sup>A100 TensorRT<br>(ms) | parámetros<br><sup>(M) | FLOPs<br><sup>(B) a 640 | | Modelo | tamaño<br><sup>(píxeles) | acc<br><sup>top1 | acc<br><sup>top5 | Velocidad<br><sup>CPU ONNX<br>(ms) | Velocidad<br><sup>A100 TensorRT<br>(ms) | parámetros<br><sup>(M) | FLOPs<br><sup>(B) a 640 |
| -------------------------------------------------------------------------------------------- | ----------------------- | ---------------- | ---------------- | -------------------------------- | --------------------------------------- | ---------------------- | ------------------------ | | -------------------------------------------------------------------------------------------- | ----------------------- | ---------------- | ---------------- | -------------------------------- | --------------------------------------- | ---------------------- | ------------------------ |
| [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-cls.pt) | 224 | 66.6 | 87.0 | 12.9 | 0.31 | 2.7 | 4.3 | | [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-cls.pt) | 224 | 66.6 | 87.0 | 12.9 | 0.31 | 2.7 | 4.3 |
| [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-cls.pt) | 224 | 72.3 | 91.1 | 23.4 | 0.35 | 6.4 | 13.5 | | [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-cls.pt) | 224 | 72.3 | 91.1 | 23.4 | 0.35 | 6.4 | 13.5 |
| [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-cls.pt) | 224 | 76.4 | 93.2 | 85.4 | 0.62 | 17.0 | 42.7 | | [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-cls.pt) | 224 | 76.4 | 93.2 | 85.4 | 0.62 | 17.0 | 42.7 |
| [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-cls.pt) | 224 | 78.0 | 94.1 | 163.0 | 0.87 | 37.5 | 99.7 | | [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-cls.pt) | 224 | 78.0 | 94.1 | 163.0 | 0.87 | 37.5 | 99.7 |
| [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-cls.pt) | 224 | 78.4 | 94.3 | 232.0 | 1.01 | 57.4 | 154.8 | | [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-cls.pt) | 224 | 78.4 | 94.3 | 232.0 | 1.01 | 57.4 | 154.8 |
=== "Pose (COCO)" === "Pose (COCO)"
@ -92,12 +92,12 @@ Esta tabla proporciona una descripción general de las variantes de modelos YOLO
| Modelo | tamaño<br><sup>(píxeles) | mAP<sup>pose<br>50-95 | mAP<sup>pose<br>50 | Velocidad<br><sup>CPU ONNX<br>(ms) | Velocidad<br><sup>A100 TensorRT<br>(ms) | parámetros<br><sup>(M) | FLOPs<br><sup>(B) | | Modelo | tamaño<br><sup>(píxeles) | mAP<sup>pose<br>50-95 | mAP<sup>pose<br>50 | Velocidad<br><sup>CPU ONNX<br>(ms) | Velocidad<br><sup>A100 TensorRT<br>(ms) | parámetros<br><sup>(M) | FLOPs<br><sup>(B) |
| ---------------------------------------------------------------------------------------------------- | ----------------------- | --------------------- | ------------------ | -------------------------------- | --------------------------------------- | ---------------------- | ----------------- | | ---------------------------------------------------------------------------------------------------- | ----------------------- | --------------------- | ------------------ | -------------------------------- | --------------------------------------- | ---------------------- | ----------------- |
| [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 | | [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 |
| [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 | | [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 |
| [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 | | [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 |
| [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 | | [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 |
| [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 | | [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 |
| [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 | | [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 |
## Ejemplos de uso ## Ejemplos de uso

10
docs/es/tasks/classify.md
View File

@ -24,11 +24,11 @@ Los [modelos](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/c
| Modelo | Tamaño<br><sup>(píxeles) | Exactitud<br><sup>top1 | Exactitud<br><sup>top5 | Velocidad<br><sup>CPU ONNX<br>(ms) | Velocidad<br><sup>A100 TensorRT<br>(ms) | Parámetros<br><sup>(M) | FLOPs<br><sup>(B) en 640 | | Modelo | Tamaño<br><sup>(píxeles) | Exactitud<br><sup>top1 | Exactitud<br><sup>top5 | Velocidad<br><sup>CPU ONNX<br>(ms) | Velocidad<br><sup>A100 TensorRT<br>(ms) | Parámetros<br><sup>(M) | FLOPs<br><sup>(B) en 640 |
|----------------------------------------------------------------------------------------------|--------------------------|------------------------|------------------------|------------------------------------|-----------------------------------------|------------------------|--------------------------| |----------------------------------------------------------------------------------------------|--------------------------|------------------------|------------------------|------------------------------------|-----------------------------------------|------------------------|--------------------------|
| [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-cls.pt) | 224 | 66.6 | 87.0 | 12.9 | 0.31 | 2.7 | 4.3 | | [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-cls.pt) | 224 | 66.6 | 87.0 | 12.9 | 0.31 | 2.7 | 4.3 |
| [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-cls.pt) | 224 | 72.3 | 91.1 | 23.4 | 0.35 | 6.4 | 13.5 | | [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-cls.pt) | 224 | 72.3 | 91.1 | 23.4 | 0.35 | 6.4 | 13.5 |
| [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-cls.pt) | 224 | 76.4 | 93.2 | 85.4 | 0.62 | 17.0 | 42.7 | | [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-cls.pt) | 224 | 76.4 | 93.2 | 85.4 | 0.62 | 17.0 | 42.7 |
| [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-cls.pt) | 224 | 78.0 | 94.1 | 163.0 | 0.87 | 37.5 | 99.7 | | [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-cls.pt) | 224 | 78.0 | 94.1 | 163.0 | 0.87 | 37.5 | 99.7 |
| [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-cls.pt) | 224 | 78.4 | 94.3 | 232.0 | 1.01 | 57.4 | 154.8 | | [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-cls.pt) | 224 | 78.4 | 94.3 | 232.0 | 1.01 | 57.4 | 154.8 |
- Los valores de **Exactitud** son las precisiones de los modelos en el conjunto de datos de validación de [ImageNet](https://www.image-net.org/). - Los valores de **Exactitud** son las precisiones de los modelos en el conjunto de datos de validación de [ImageNet](https://www.image-net.org/).
<br>Para reproducir usar `yolo val classify data=path/to/ImageNet device=0` <br>Para reproducir usar `yolo val classify data=path/to/ImageNet device=0`

10
docs/es/tasks/detect.md
View File

@ -35,11 +35,11 @@ Los [modelos](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/c
| Modelo | tamaño<br><sup>(píxeles) | mAP<sup>val<br>50-95 | Velocidad<br><sup>CPU ONNX<br>(ms) | Velocidad<br><sup>A100 TensorRT<br>(ms) | parámetros<br><sup>(M) | FLOPs<br><sup>(B) | | Modelo | tamaño<br><sup>(píxeles) | mAP<sup>val<br>50-95 | Velocidad<br><sup>CPU ONNX<br>(ms) | Velocidad<br><sup>A100 TensorRT<br>(ms) | parámetros<br><sup>(M) | FLOPs<br><sup>(B) |
|--------------------------------------------------------------------------------------|--------------------------|----------------------|------------------------------------|-----------------------------------------|------------------------|-------------------| |--------------------------------------------------------------------------------------|--------------------------|----------------------|------------------------------------|-----------------------------------------|------------------------|-------------------|
| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 | | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 |
| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 | | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 |
| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 | | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 |
| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 | | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 |
| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 | | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 |
- Los valores de **mAP<sup>val</sup>** son para un solo modelo a una sola escala en el conjunto de datos [COCO val2017](http://cocodataset.org). - Los valores de **mAP<sup>val</sup>** son para un solo modelo a una sola escala en el conjunto de datos [COCO val2017](http://cocodataset.org).
<br>Reproduce utilizando `yolo val detect data=coco.yaml device=0` <br>Reproduce utilizando `yolo val detect data=coco.yaml device=0`

12
docs/es/tasks/pose.md
View File

@ -35,12 +35,12 @@ Los [modelos](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/c
| Modelo | tamaño<br><sup>(píxeles) | mAP<sup>pose<br>50-95 | mAP<sup>pose<br>50 | Velocidad<br><sup>CPU ONNX<br>(ms) | Velocidad<br><sup>A100 TensorRT<br>(ms) | parámetros<br><sup>(M) | FLOPs<br><sup>(B) | | Modelo | tamaño<br><sup>(píxeles) | mAP<sup>pose<br>50-95 | mAP<sup>pose<br>50 | Velocidad<br><sup>CPU ONNX<br>(ms) | Velocidad<br><sup>A100 TensorRT<br>(ms) | parámetros<br><sup>(M) | FLOPs<br><sup>(B) |
|------------------------------------------------------------------------------------------------------|--------------------------|-----------------------|--------------------|------------------------------------|-----------------------------------------|------------------------|-------------------| |------------------------------------------------------------------------------------------------------|--------------------------|-----------------------|--------------------|------------------------------------|-----------------------------------------|------------------------|-------------------|
| [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 | | [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 |
| [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 | | [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 |
| [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 | | [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 |
| [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 | | [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 |
| [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 | | [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 |
| [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 | | [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 |
- Los valores de **mAP<sup>val</sup>** son para un solo modelo a una sola escala en el conjunto de datos [COCO Keypoints val2017](http://cocodataset.org). - Los valores de **mAP<sup>val</sup>** son para un solo modelo a una sola escala en el conjunto de datos [COCO Keypoints val2017](http://cocodataset.org).
<br>Reproducir con `yolo val pose data=coco-pose.yaml device=0` <br>Reproducir con `yolo val pose data=coco-pose.yaml device=0`

10
docs/es/tasks/segment.md
View File

@ -35,11 +35,11 @@ Los [Modelos](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/c
| Modelo | Tamaño<br><sup>(píxeles) | mAP<sup>caja<br>50-95 | mAP<sup>máscara<br>50-95 | Velocidad<br><sup>CPU ONNX<br>(ms) | Velocidad<br><sup>A100 TensorRT<br>(ms) | Parámetros<br><sup>(M) | FLOPs<br><sup>(B) | | Modelo | Tamaño<br><sup>(píxeles) | mAP<sup>caja<br>50-95 | mAP<sup>máscara<br>50-95 | Velocidad<br><sup>CPU ONNX<br>(ms) | Velocidad<br><sup>A100 TensorRT<br>(ms) | Parámetros<br><sup>(M) | FLOPs<br><sup>(B) |
|----------------------------------------------------------------------------------------------|--------------------------|-----------------------|--------------------------|------------------------------------|-----------------------------------------|------------------------|-------------------| |----------------------------------------------------------------------------------------------|--------------------------|-----------------------|--------------------------|------------------------------------|-----------------------------------------|------------------------|-------------------|
| [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 | | [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 |
| [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 | | [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 |
| [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 | | [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 |
| [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 | | [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 |
| [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 | | [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 |
- Los valores **mAP<sup>val</sup>** son para un único modelo a una única escala en el conjunto de datos [COCO val2017](http://cocodataset.org). - Los valores **mAP<sup>val</sup>** son para un único modelo a una única escala en el conjunto de datos [COCO val2017](http://cocodataset.org).
<br>Reproducir utilizando `yolo val segment data=coco.yaml device=0` <br>Reproducir utilizando `yolo val segment data=coco.yaml device=0`

6
docs/fr/models/yolo-nas.md
View File

@ -92,9 +92,9 @@ Voici un aperçu détaillé de chaque modèle, comprenant des liens vers leurs p
| Type de modèle | Poids pré-entraînés | Tâches prises en charge | Inférence | Validation | Entraînement | Export | | Type de modèle | Poids pré-entraînés | Tâches prises en charge | Inférence | Validation | Entraînement | Export |
|----------------|-----------------------------------------------------------------------------------------------|------------------------------------------|-----------|------------|--------------|--------| |----------------|-----------------------------------------------------------------------------------------------|------------------------------------------|-----------|------------|--------------|--------|
| YOLO-NAS-s | [yolo_nas_s.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolo_nas_s.pt) | [Détection d'objets](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ | | YOLO-NAS-s | [yolo_nas_s.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolo_nas_s.pt) | [Détection d'objets](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ |
| YOLO-NAS-m | [yolo_nas_m.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolo_nas_m.pt) | [Détection d'objets](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ | | YOLO-NAS-m | [yolo_nas_m.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolo_nas_m.pt) | [Détection d'objets](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ |
| YOLO-NAS-l | [yolo_nas_l.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolo_nas_l.pt) | [Détection d'objets](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ | | YOLO-NAS-l | [yolo_nas_l.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolo_nas_l.pt) | [Détection d'objets](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ |
## Citations et remerciements ## Citations et remerciements

20
docs/fr/models/yolov5.md
View File

@ -40,17 +40,17 @@ Ce tableau fournit un aperçu détaillé des variantes de modèles YOLOv5u, mett
| Modèle | YAML | taille<br><sup>(pixels) | mAP<sup>val<br>50-95 | Vitesse<br><sup>CPU ONNX<br>(ms) | Vitesse<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) | | Modèle | YAML | taille<br><sup>(pixels) | mAP<sup>val<br>50-95 | Vitesse<br><sup>CPU ONNX<br>(ms) | Vitesse<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) |
|-------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------|-----------------------|----------------------|--------------------------------|-------------------------------------|--------------------|-------------------| |-------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------|-----------------------|----------------------|--------------------------------|-------------------------------------|--------------------|-------------------|
| [yolov5nu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5nu.pt) | [yolov5n.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 34,3 | 73,6 | 1,06 | 2,6 | 7,7 | | [yolov5nu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5nu.pt) | [yolov5n.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 34,3 | 73,6 | 1,06 | 2,6 | 7,7 |
| [yolov5su.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5su.pt) | [yolov5s.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 43,0 | 120,7 | 1,27 | 9,1 | 24,0 | | [yolov5su.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5su.pt) | [yolov5s.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 43,0 | 120,7 | 1,27 | 9,1 | 24,0 |
| [yolov5mu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5mu.pt) | [yolov5m.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 49,0 | 233,9 | 1,86 | 25,1 | 64,2 | | [yolov5mu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5mu.pt) | [yolov5m.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 49,0 | 233,9 | 1,86 | 25,1 | 64,2 |
| [yolov5lu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5lu.pt) | [yolov5l.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 52,2 | 408,4 | 2,50 | 53,2 | 135,0 | | [yolov5lu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5lu.pt) | [yolov5l.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 52,2 | 408,4 | 2,50 | 53,2 | 135,0 |
| [yolov5xu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5xu.pt) | [yolov5x.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 53,2 | 763,2 | 3,81 | 97,2 | 246,4 | | [yolov5xu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5xu.pt) | [yolov5x.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 53,2 | 763,2 | 3,81 | 97,2 | 246,4 |
| | | | | | | | | | | | | | | | | |
| [yolov5n6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5n6u.pt) | [yolov5n6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 42,1 | 211,0 | 1,83 | 4,3 | 7,8 | | [yolov5n6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5n6u.pt) | [yolov5n6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 42,1 | 211,0 | 1,83 | 4,3 | 7,8 |
| [yolov5s6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5s6u.pt) | [yolov5s6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 48,6 | 422,6 | 2,34 | 15,3 | 24,6 | | [yolov5s6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5s6u.pt) | [yolov5s6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 48,6 | 422,6 | 2,34 | 15,3 | 24,6 |
| [yolov5m6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5m6u.pt) | [yolov5m6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 53,6 | 810,9 | 4,36 | 41,2 | 65,7 | | [yolov5m6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5m6u.pt) | [yolov5m6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 53,6 | 810,9 | 4,36 | 41,2 | 65,7 |
| [yolov5l6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5l6u.pt) | [yolov5l6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 55,7 | 1470,9 | 5,47 | 86,1 | 137,4 | | [yolov5l6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5l6u.pt) | [yolov5l6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 55,7 | 1470,9 | 5,47 | 86,1 | 137,4 |
| [yolov5x6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5x6u.pt) | [yolov5x6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 56,8 | 2436,5 | 8,98 | 155,4 | 250,7 | | [yolov5x6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5x6u.pt) | [yolov5x6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 56,8 | 2436,5 | 8,98 | 155,4 | 250,7 |
## Exemples d'utilisation ## Exemples d'utilisation

52
docs/fr/models/yolov8.md
View File

@ -44,11 +44,11 @@ Ce tableau donne un aperçu des variantes des modèles YOLOv8, mettant en évide
| Modèle | taille<br><sup>(pixels) | mAP<sup>val<br>50-95 | Vitesse<br><sup>CPU ONNX<br>(ms) | Vitesse<br><sup>A100 TensorRT<br>(ms) | paramètres<br><sup>(M) | FLOPs<br><sup>(B) | | Modèle | taille<br><sup>(pixels) | mAP<sup>val<br>50-95 | Vitesse<br><sup>CPU ONNX<br>(ms) | Vitesse<br><sup>A100 TensorRT<br>(ms) | paramètres<br><sup>(M) | FLOPs<br><sup>(B) |
| ------------------------------------------------------------------------------------ | --------------------- | -------------------- | ------------------------------- | ------------------------------------ | ------------------ | ----------------- | | ------------------------------------------------------------------------------------ | --------------------- | -------------------- | ------------------------------- | ------------------------------------ | ------------------ | ----------------- |
| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt) | 640 | 37,3 | 80,4 | 0,99 | 3,2 | 8,7 | | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt) | 640 | 37,3 | 80,4 | 0,99 | 3,2 | 8,7 |
| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s.pt) | 640 | 44,9 | 128,4 | 1,20 | 11,2 | 28,6 | | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s.pt) | 640 | 44,9 | 128,4 | 1,20 | 11,2 | 28,6 |
| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m.pt) | 640 | 50,2 | 234,7 | 1,83 | 25,9 | 78,9 | | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m.pt) | 640 | 50,2 | 234,7 | 1,83 | 25,9 | 78,9 |
| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l.pt) | 640 | 52,9 | 375,2 | 2,39 | 43,7 | 165,2 | | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l.pt) | 640 | 52,9 | 375,2 | 2,39 | 43,7 | 165,2 |
| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x.pt) | 640 | 53,9 | 479,1 | 3,53 | 68,2 | 257,8 | | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x.pt) | 640 | 53,9 | 479,1 | 3,53 | 68,2 | 257,8 |
=== "Détection (Open Images V7)" === "Détection (Open Images V7)"
@ -56,11 +56,11 @@ Ce tableau donne un aperçu des variantes des modèles YOLOv8, mettant en évide
| Modèle | taille<br><sup>(pixels) | mAP<sup>val<br>50-95 | Vitesse<br><sup>CPU ONNX<br>(ms) | Vitesse<br><sup>A100 TensorRT<br>(ms) | paramètres<br><sup>(M) | FLOPs<br><sup>(B) | | Modèle | taille<br><sup>(pixels) | mAP<sup>val<br>50-95 | Vitesse<br><sup>CPU ONNX<br>(ms) | Vitesse<br><sup>A100 TensorRT<br>(ms) | paramètres<br><sup>(M) | FLOPs<br><sup>(B) |
| ----------------------------------------------------------------------------------------- | --------------------- | -------------------- | ------------------------------- | ------------------------------------ | ------------------ | ----------------- | | ----------------------------------------------------------------------------------------- | --------------------- | -------------------- | ------------------------------- | ------------------------------------ | ------------------ | ----------------- |
| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-oiv7.pt) | 640 | 18,4 | 142,4 | 1,21 | 3,5 | 10,5 | | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-oiv7.pt) | 640 | 18,4 | 142,4 | 1,21 | 3,5 | 10,5 |
| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-oiv7.pt) | 640 | 27,7 | 183,1 | 1,40 | 11,4 | 29,7 | | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-oiv7.pt) | 640 | 27,7 | 183,1 | 1,40 | 11,4 | 29,7 |
| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-oiv7.pt) | 640 | 33,6 | 408,5 | 2,26 | 26,2 | 80,6 | | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-oiv7.pt) | 640 | 33,6 | 408,5 | 2,26 | 26,2 | 80,6 |
| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-oiv7.pt) | 640 | 34,9 | 596,9 | 2,43 | 44,1 | 167,4 | | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-oiv7.pt) | 640 | 34,9 | 596,9 | 2,43 | 44,1 | 167,4 |
| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-oiv7.pt) | 640 | 36,3 | 860,6 | 3,56 | 68,7 | 260,6 | | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-oiv7.pt) | 640 | 36,3 | 860,6 | 3,56 | 68,7 | 260,6 |
=== "Segmentation (COCO)" === "Segmentation (COCO)"
@ -68,11 +68,11 @@ Ce tableau donne un aperçu des variantes des modèles YOLOv8, mettant en évide
| Modèle | taille<br><sup>(pixels) | mAP<sup>box<br>50-95 | mAP<sup>mask<br>50-95 | Vitesse<br><sup>CPU ONNX<br>(ms) | Vitesse<br><sup>A100 TensorRT<br>(ms) | paramètres<br><sup>(M) | FLOPs<br><sup>(B) | | Modèle | taille<br><sup>(pixels) | mAP<sup>box<br>50-95 | mAP<sup>mask<br>50-95 | Vitesse<br><sup>CPU ONNX<br>(ms) | Vitesse<br><sup>A100 TensorRT<br>(ms) | paramètres<br><sup>(M) | FLOPs<br><sup>(B) |
| -------------------------------------------------------------------------------------------- | --------------------- | -------------------- | --------------------- | ------------------------------- | ------------------------------------ | ------------------ | ----------------- | | -------------------------------------------------------------------------------------------- | --------------------- | -------------------- | --------------------- | ------------------------------- | ------------------------------------ | ------------------ | ----------------- |
| [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-seg.pt) | 640 | 36,7 | 30,5 | 96,1 | 1,21 | 3,4 | 12,6 | | [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-seg.pt) | 640 | 36,7 | 30,5 | 96,1 | 1,21 | 3,4 | 12,6 |
| [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-seg.pt) | 640 | 44,6 | 36,8 | 155,7 | 1,47 | 11,8 | 42,6 | | [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-seg.pt) | 640 | 44,6 | 36,8 | 155,7 | 1,47 | 11,8 | 42,6 |
| [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-seg.pt) | 640 | 49,9 | 40,8 | 317,0 | 2,18 | 27,3 | 110,2 | | [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-seg.pt) | 640 | 49,9 | 40,8 | 317,0 | 2,18 | 27,3 | 110,2 |
| [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-seg.pt) | 640 | 52,3 | 42,6 | 572,4 | 2,79 | 46,0 | 220,5 | | [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-seg.pt) | 640 | 52,3 | 42,6 | 572,4 | 2,79 | 46,0 | 220,5 |
| [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-seg.pt) | 640 | 53,4 | 43,4 | 712,1 | 4,02 | 71,8 | 344,1 | | [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-seg.pt) | 640 | 53,4 | 43,4 | 712,1 | 4,02 | 71,8 | 344,1 |
=== "Classification (ImageNet)" === "Classification (ImageNet)"
@ -80,11 +80,11 @@ Ce tableau donne un aperçu des variantes des modèles YOLOv8, mettant en évide
| Modèle | taille<br><sup>(pixels) | acc<br><sup>top1 | acc<br><sup>top5 | Vitesse<br><sup>CPU ONNX<br>(ms) | Vitesse<br><sup>A100 TensorRT<br>(ms) | paramètres<br><sup>(M) | FLOPs<br><sup>(B) at 640 | | Modèle | taille<br><sup>(pixels) | acc<br><sup>top1 | acc<br><sup>top5 | Vitesse<br><sup>CPU ONNX<br>(ms) | Vitesse<br><sup>A100 TensorRT<br>(ms) | paramètres<br><sup>(M) | FLOPs<br><sup>(B) at 640 |
| -------------------------------------------------------------------------------------------- | --------------------- | ---------------- | ---------------- | ------------------------------- | ------------------------------------ | ------------------ | ------------------------ | | -------------------------------------------------------------------------------------------- | --------------------- | ---------------- | ---------------- | ------------------------------- | ------------------------------------ | ------------------ | ------------------------ |
| [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-cls.pt) | 224 | 66,6 | 87,0 | 12,9 | 0,31 | 2,7 | 4,3 | | [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-cls.pt) | 224 | 66,6 | 87,0 | 12,9 | 0,31 | 2,7 | 4,3 |
| [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-cls.pt) | 224 | 72,3 | 91,1 | 23,4 | 0,35 | 6,4 | 13,5 | | [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-cls.pt) | 224 | 72,3 | 91,1 | 23,4 | 0,35 | 6,4 | 13,5 |
| [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-cls.pt) | 224 | 76,4 | 93,2 | 85,4 | 0,62 | 17,0 | 42,7 | | [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-cls.pt) | 224 | 76,4 | 93,2 | 85,4 | 0,62 | 17,0 | 42,7 |
| [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-cls.pt) | 224 | 78,0 | 94,1 | 163,0 | 0,87 | 37,5 | 99,7 | | [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-cls.pt) | 224 | 78,0 | 94,1 | 163,0 | 0,87 | 37,5 | 99,7 |
| [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-cls.pt) | 224 | 78,4 | 94,3 | 232,0 | 1,01 | 57,4 | 154,8 | | [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-cls.pt) | 224 | 78,4 | 94,3 | 232,0 | 1,01 | 57,4 | 154,8 |
=== "Pose (COCO)" === "Pose (COCO)"
@ -92,12 +92,12 @@ Ce tableau donne un aperçu des variantes des modèles YOLOv8, mettant en évide
| Modèle | taille<br><sup>(pixels) | mAP<sup>pose<br>50-95 | mAP<sup>pose<br>50 | Vitesse<br><sup>CPU ONNX<br>(ms) | Vitesse<br><sup>A100 TensorRT<br>(ms) | paramètres<br><sup>(M) | FLOPs<br><sup>(B) | | Modèle | taille<br><sup>(pixels) | mAP<sup>pose<br>50-95 | mAP<sup>pose<br>50 | Vitesse<br><sup>CPU ONNX<br>(ms) | Vitesse<br><sup>A100 TensorRT<br>(ms) | paramètres<br><sup>(M) | FLOPs<br><sup>(B) |
| ---------------------------------------------------------------------------------------------------- | --------------------- | --------------------- | ------------------ | ------------------------------- | ------------------------------------ | ------------------ | ----------------- | | ---------------------------------------------------------------------------------------------------- | --------------------- | --------------------- | ------------------ | ------------------------------- | ------------------------------------ | ------------------ | ----------------- |
| [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-pose.pt) | 640 | 50,4 | 80,1 | 131,8 | 1,18 | 3,3 | 9,2 | | [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-pose.pt) | 640 | 50,4 | 80,1 | 131,8 | 1,18 | 3,3 | 9,2 |
| [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-pose.pt) | 640 | 60,0 | 86,2 | 233,2 | 1,42 | 11,6 | 30,2 | | [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-pose.pt) | 640 | 60,0 | 86,2 | 233,2 | 1,42 | 11,6 | 30,2 |
| [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-pose.pt) | 640 | 65,0 | 88,8 | 456,3 | 2,00 | 26,4 | 81,0 | | [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-pose.pt) | 640 | 65,0 | 88,8 | 456,3 | 2,00 | 26,4 | 81,0 |
| [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-pose.pt) | 640 | 67,6 | 90,0 | 784,5 | 2,59 | 44,4 | 168,6 | | [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-pose.pt) | 640 | 67,6 | 90,0 | 784,5 | 2,59 | 44,4 | 168,6 |
| [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose.pt) | 640 | 69,2 | 90,2 | 1607,1 | 3,73 | 69,4 | 263,2 | | [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose.pt) | 640 | 69,2 | 90,2 | 1607,1 | 3,73 | 69,4 | 263,2 |
| [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose-p6.pt) | 1280 | 71,6 | 91,2 | 4088,7 | 10,04 | 99,1 | 1066,4 | | [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose-p6.pt) | 1280 | 71,6 | 91,2 | 4088,7 | 10,04 | 99,1 | 1066,4 |
## Exemples d'utilisation ## Exemples d'utilisation

10
docs/fr/tasks/classify.md
View File

@ -24,11 +24,11 @@ Les [modèles](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/
| Modèle | taille<br><sup>(pixels) | acc<br><sup>top1 | acc<br><sup>top5 | Vitesse<br><sup>CPU ONNX<br>(ms) | Vitesse<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) à 640 | | Modèle | taille<br><sup>(pixels) | acc<br><sup>top1 | acc<br><sup>top5 | Vitesse<br><sup>CPU ONNX<br>(ms) | Vitesse<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) à 640 |
|----------------------------------------------------------------------------------------------|-------------------------|------------------|------------------|----------------------------------|---------------------------------------|--------------------|-------------------------| |----------------------------------------------------------------------------------------------|-------------------------|------------------|------------------|----------------------------------|---------------------------------------|--------------------|-------------------------|
| [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-cls.pt) | 224 | 66.6 | 87.0 | 12.9 | 0.31 | 2.7 | 4.3 | | [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-cls.pt) | 224 | 66.6 | 87.0 | 12.9 | 0.31 | 2.7 | 4.3 |
| [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-cls.pt) | 224 | 72.3 | 91.1 | 23.4 | 0.35 | 6.4 | 13.5 | | [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-cls.pt) | 224 | 72.3 | 91.1 | 23.4 | 0.35 | 6.4 | 13.5 |
| [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-cls.pt) | 224 | 76.4 | 93.2 | 85.4 | 0.62 | 17.0 | 42.7 | | [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-cls.pt) | 224 | 76.4 | 93.2 | 85.4 | 0.62 | 17.0 | 42.7 |
| [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-cls.pt) | 224 | 78.0 | 94.1 | 163.0 | 0.87 | 37.5 | 99.7 | | [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-cls.pt) | 224 | 78.0 | 94.1 | 163.0 | 0.87 | 37.5 | 99.7 |
| [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-cls.pt) | 224 | 78.4 | 94.3 | 232.0 | 1.01 | 57.4 | 154.8 | | [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-cls.pt) | 224 | 78.4 | 94.3 | 232.0 | 1.01 | 57.4 | 154.8 |
- Les valeurs **acc** sont les précisions des modèles sur le jeu de données de validation d'[ImageNet](https://www.image-net.org/). - Les valeurs **acc** sont les précisions des modèles sur le jeu de données de validation d'[ImageNet](https://www.image-net.org/).
<br>Pour reproduire : `yolo val classify data=path/to/ImageNet device=0` <br>Pour reproduire : `yolo val classify data=path/to/ImageNet device=0`

10
docs/fr/tasks/detect.md
View File

@ -35,11 +35,11 @@ Les modèles pré-entraînés Detect YOLOv8 sont présentés ici. Les modèles D
| Modèle | Taille<br><sup>(pixels) | mAP<sup>val<br>50-95 | Vitesse<br><sup>CPU ONNX<br>(ms) | Vitesse<br><sup>A100 TensorRT<br>(ms) | Paramètres<br><sup>(M) | FLOPs<br><sup>(B) | | Modèle | Taille<br><sup>(pixels) | mAP<sup>val<br>50-95 | Vitesse<br><sup>CPU ONNX<br>(ms) | Vitesse<br><sup>A100 TensorRT<br>(ms) | Paramètres<br><sup>(M) | FLOPs<br><sup>(B) |
|--------------------------------------------------------------------------------------|-------------------------|----------------------|----------------------------------|---------------------------------------|------------------------|-------------------| |--------------------------------------------------------------------------------------|-------------------------|----------------------|----------------------------------|---------------------------------------|------------------------|-------------------|
| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 | | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 |
| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 | | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 |
| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 | | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 |
| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 | | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 |
| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 | | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 |
- Les valeurs de **mAP<sup>val</sup>** sont pour un seul modèle à une seule échelle sur le jeu de données [COCO val2017](http://cocodataset.org). - Les valeurs de **mAP<sup>val</sup>** sont pour un seul modèle à une seule échelle sur le jeu de données [COCO val2017](http://cocodataset.org).
<br>Reproductible avec `yolo val detect data=coco.yaml device=0` <br>Reproductible avec `yolo val detect data=coco.yaml device=0`

12
docs/fr/tasks/pose.md
View File

@ -26,12 +26,12 @@ Les [Modèles](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/
| Modèle | taille<br><sup>(pixels) | mAP<sup>pose<br>50-95 | mAP<sup>pose<br>50 | Vitesse<br><sup>CPU ONNX<br>(ms) | Vitesse<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) | | Modèle | taille<br><sup>(pixels) | mAP<sup>pose<br>50-95 | mAP<sup>pose<br>50 | Vitesse<br><sup>CPU ONNX<br>(ms) | Vitesse<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) |
|------------------------------------------------------------------------------------------------------|-------------------------|-----------------------|--------------------|----------------------------------|---------------------------------------|--------------------|-------------------| |------------------------------------------------------------------------------------------------------|-------------------------|-----------------------|--------------------|----------------------------------|---------------------------------------|--------------------|-------------------|
| [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 | | [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 |
| [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 | | [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 |
| [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 | | [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 |
| [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 | | [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 |
| [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 | | [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 |
| [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 | | [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 |
- Les valeurs de **mAP<sup>val</sup>** sont pour un seul modèle à une seule échelle sur le jeu de données [COCO Keypoints val2017](http://cocodataset.org). - Les valeurs de **mAP<sup>val</sup>** sont pour un seul modèle à une seule échelle sur le jeu de données [COCO Keypoints val2017](http://cocodataset.org).
<br>Reproduire avec `yolo val pose data=coco-pose.yaml device=0` <br>Reproduire avec `yolo val pose data=coco-pose.yaml device=0`

10
docs/fr/tasks/segment.md
View File

@ -35,11 +35,11 @@ Les [modèles](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/
| Modèle | Taille<br><sup>(pixels) | mAP<sup>boîte<br>50-95 | mAP<sup>masque<br>50-95 | Vitesse<br><sup>CPU ONNX<br>(ms) | Vitesse<br><sup>A100 TensorRT<br>(ms) | Paramètres<br><sup>(M) | FLOPs<br><sup>(B) | | Modèle | Taille<br><sup>(pixels) | mAP<sup>boîte<br>50-95 | mAP<sup>masque<br>50-95 | Vitesse<br><sup>CPU ONNX<br>(ms) | Vitesse<br><sup>A100 TensorRT<br>(ms) | Paramètres<br><sup>(M) | FLOPs<br><sup>(B) |
|----------------------------------------------------------------------------------------------|-------------------------|------------------------|-------------------------|----------------------------------|---------------------------------------|------------------------|-------------------| |----------------------------------------------------------------------------------------------|-------------------------|------------------------|-------------------------|----------------------------------|---------------------------------------|------------------------|-------------------|
| [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 | | [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 |
| [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 | | [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 |
| [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 | | [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 |
| [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 | | [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 |
| [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 | | [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 |
- Les valeurs **mAP<sup>val</sup>** sont pour un seul modèle à une seule échelle sur le jeu de données [COCO val2017](http://cocodataset.org). - Les valeurs **mAP<sup>val</sup>** sont pour un seul modèle à une seule échelle sur le jeu de données [COCO val2017](http://cocodataset.org).
<br>Pour reproduire, utilisez `yolo val segment data=coco.yaml device=0` <br>Pour reproduire, utilisez `yolo val segment data=coco.yaml device=0`

6
docs/hi/models/yolo-nas.md
View File

@ -92,9 +92,9 @@ Ultralytics ने YOLO-NAS मॉडलों को आपके Python ऐप
| मॉडल प्रकार | प्री-प्रशित वेट | समर्थित कार्य | पहचान | मान्यता | प्रशिक्षण | निर्यात | | मॉडल प्रकार | प्री-प्रशित वेट | समर्थित कार्य | पहचान | मान्यता | प्रशिक्षण | निर्यात |
|-------------|-----------------------------------------------------------------------------------------------|-----------------------------------|-------|---------|-----------|---------| |-------------|-----------------------------------------------------------------------------------------------|-----------------------------------|-------|---------|-----------|---------|
| YOLO-NAS-s | [yolo_nas_s.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolo_nas_s.pt) | [वस्तु पहचान](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ | | YOLO-NAS-s | [yolo_nas_s.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolo_nas_s.pt) | [वस्तु पहचान](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ |
| YOLO-NAS-m | [yolo_nas_m.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolo_nas_m.pt) | [वस्तु पहचान](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ | | YOLO-NAS-m | [yolo_nas_m.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolo_nas_m.pt) | [वस्तु पहचान](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ |
| YOLO-NAS-l | [yolo_nas_l.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolo_nas_l.pt) | [वस्तु पहचान](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ | | YOLO-NAS-l | [yolo_nas_l.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolo_nas_l.pt) | [वस्तु पहचान](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ |
## उद्धरण और प्रशंसापत्र ## उद्धरण और प्रशंसापत्र

20
docs/hi/models/yolov5.md
View File

@ -40,17 +40,17 @@ YOLOv5u वस्तु ज्ञापन के तरीकों में
| मॉडल | YAML | साइज़<br><sup>(पिक्सेल) | mAP<sup>वैल<br>50-95 | गति<br><sup>CPU ONNX<br>(मि.से.) | गति<br><sup>A100 TensorRT<br>(मि.से.) | params<sup><br>(M) | FLOPs<sup><br>(B) | | मॉडल | YAML | साइज़<br><sup>(पिक्सेल) | mAP<sup>वैल<br>50-95 | गति<br><sup>CPU ONNX<br>(मि.से.) | गति<br><sup>A100 TensorRT<br>(मि.से.) | params<sup><br>(M) | FLOPs<sup><br>(B) |
|---------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------|---------------------------|------------------------|--------------------------------|-----------------------------------------|--------------------|-------------------| |---------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------|---------------------------|------------------------|--------------------------------|-----------------------------------------|--------------------|-------------------|
| [yolov5nu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5nu.pt) | [yolov5n.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 34.3 | 73.6 | 1.06 | 2.6 | 7.7 | | [yolov5nu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5nu.pt) | [yolov5n.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 34.3 | 73.6 | 1.06 | 2.6 | 7.7 |
| [yolov5su.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5su.pt) | [yolov5s.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 43.0 | 120.7 | 1.27 | 9.1 | 24.0 | | [yolov5su.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5su.pt) | [yolov5s.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 43.0 | 120.7 | 1.27 | 9.1 | 24.0 |
| [yolov5mu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5mu.pt) | [yolov5m.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 49.0 | 233.9 | 1.86 | 25.1 | 64.2 | | [yolov5mu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5mu.pt) | [yolov5m.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 49.0 | 233.9 | 1.86 | 25.1 | 64.2 |
| [yolov5lu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5lu.pt) | [yolov5l.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 52.2 | 408.4 | 2.50 | 53.2 | 135.0 | | [yolov5lu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5lu.pt) | [yolov5l.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 52.2 | 408.4 | 2.50 | 53.2 | 135.0 |
| [yolov5xu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5xu.pt) | [yolov5x.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 53.2 | 763.2 | 3.81 | 97.2 | 246.4 | | [yolov5xu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5xu.pt) | [yolov5x.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 53.2 | 763.2 | 3.81 | 97.2 | 246.4 |
| | | | | | | | | | | | | | | | | |
| [yolov5n6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5n6u.pt) | [yolov5n6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 42.1 | 211.0 | 1.83 | 4.3 | 7.8 | | [yolov5n6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5n6u.pt) | [yolov5n6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 42.1 | 211.0 | 1.83 | 4.3 | 7.8 |
| [yolov5s6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5s6u.pt) | [yolov5s6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 48.6 | 422.6 | 2.34 | 15.3 | 24.6 | | [yolov5s6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5s6u.pt) | [yolov5s6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 48.6 | 422.6 | 2.34 | 15.3 | 24.6 |
| [yolov5m6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5m6u.pt) | [yolov5m6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 53.6 | 810.9 | 4.36 | 41.2 | 65.7 | | [yolov5m6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5m6u.pt) | [yolov5m6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 53.6 | 810.9 | 4.36 | 41.2 | 65.7 |
| [yolov5l6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5l6u.pt) | [yolov5l6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 55.7 | 1470.9 | 5.47 | 86.1 | 137.4 | | [yolov5l6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5l6u.pt) | [yolov5l6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 55.7 | 1470.9 | 5.47 | 86.1 | 137.4 |
| [yolov5x6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5x6u.pt) | [yolov5x6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 56.8 | 2436.5 | 8.98 | 155.4 | 250.7 | | [yolov5x6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5x6u.pt) | [yolov5x6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 56.8 | 2436.5 | 8.98 | 155.4 | 250.7 |
## उपयोग उदाहरण ## उपयोग उदाहरण

52
docs/hi/models/yolov8.md
View File

@ -44,11 +44,11 @@ Yएक मॉडल के हर मानक, विशिष्ट कार
| मॉडल | आकार<br><sup>(पिक्स) | mAP<sup>वैल<br>50-95 | गति<br><sup>CPU ONNX<br>(ms) | गति<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(एम) | FLOPs<br><sup>(बी) | | मॉडल | आकार<br><sup>(पिक्स) | mAP<sup>वैल<br>50-95 | गति<br><sup>CPU ONNX<br>(ms) | गति<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(एम) | FLOPs<br><sup>(बी) |
| ------------------------------------------------------------------------------------ | --------------------- | -------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- | | ------------------------------------------------------------------------------------ | --------------------- | -------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 | | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 |
| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 | | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 |
| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 | | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 |
| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 | | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 |
| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 | | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 |
=== "वस्तुनिर्धारण (Open Images V7)" === "वस्तुनिर्धारण (Open Images V7)"
@ -56,11 +56,11 @@ Yएक मॉडल के हर मानक, विशिष्ट कार
| मॉडल | आकार<br><sup>(पिक्स) | mAP<sup>वैल<br>50-95 | गति<br><sup>CPU ONNX<br>(ms) | गति<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(एम) | FLOPs<br><sup>(बी) | | मॉडल | आकार<br><sup>(पिक्स) | mAP<sup>वैल<br>50-95 | गति<br><sup>CPU ONNX<br>(ms) | गति<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(एम) | FLOPs<br><sup>(बी) |
| ----------------------------------------------------------------------------------------- | --------------------- | -------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- | | ----------------------------------------------------------------------------------------- | --------------------- | -------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-oiv7.pt) | 640 | 18.4 | 142.4 | 1.21 | 3.5 | 10.5 | | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-oiv7.pt) | 640 | 18.4 | 142.4 | 1.21 | 3.5 | 10.5 |
| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-oiv7.pt) | 640 | 27.7 | 183.1 | 1.40 | 11.4 | 29.7 | | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-oiv7.pt) | 640 | 27.7 | 183.1 | 1.40 | 11.4 | 29.7 |
| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-oiv7.pt) | 640 | 33.6 | 408.5 | 2.26 | 26.2 | 80.6 | | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-oiv7.pt) | 640 | 33.6 | 408.5 | 2.26 | 26.2 | 80.6 |
| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-oiv7.pt) | 640 | 34.9 | 596.9 | 2.43 | 44.1 | 167.4 | | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-oiv7.pt) | 640 | 34.9 | 596.9 | 2.43 | 44.1 | 167.4 |
| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-oiv7.pt) | 640 | 36.3 | 860.6 | 3.56 | 68.7 | 260.6 | | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-oiv7.pt) | 640 | 36.3 | 860.6 | 3.56 | 68.7 | 260.6 |
=== "सेगमेंटेशन (COCO)" === "सेगमेंटेशन (COCO)"
@ -68,11 +68,11 @@ Yएक मॉडल के हर मानक, विशिष्ट कार
| मॉडल | आकार<br><sup>(पिक्स) | mAP<sup>बॉक्स<br>50-95 | mAP<sup>मास्क<br>50-95 | गति<br><sup>CPU ONNX<br>(ms) | गति<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(एम) | FLOPs<br><sup>(बी) | | मॉडल | आकार<br><sup>(पिक्स) | mAP<sup>बॉक्स<br>50-95 | mAP<sup>मास्क<br>50-95 | गति<br><sup>CPU ONNX<br>(ms) | गति<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(एम) | FLOPs<br><sup>(बी) |
| -------------------------------------------------------------------------------------------- | --------------------- | --------------------- | --------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- | | -------------------------------------------------------------------------------------------- | --------------------- | --------------------- | --------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
| [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 | | [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 |
| [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 | | [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 |
| [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 | | [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 |
| [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 | | [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 |
| [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 | | [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 |
=== "श्रेणीकरण (ImageNet)" === "श्रेणीकरण (ImageNet)"
@ -80,11 +80,11 @@ Yएक मॉडल के हर मानक, विशिष्ट कार
| मॉडल | आकार<br><sup>(पिक्स) | शीर्ष1 विजयी<br>योग्यता | शीर्ष5 विजयी<br>योग्यता | गति<br><sup>CPU ONNX<br>(ms) | गति<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(एम) | FLOPs<br><sup>(बी) at 640 | | मॉडल | आकार<br><sup>(पिक्स) | शीर्ष1 विजयी<br>योग्यता | शीर्ष5 विजयी<br>योग्यता | गति<br><sup>CPU ONNX<br>(ms) | गति<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(एम) | FLOPs<br><sup>(बी) at 640 |
| ------------------------------------------------------------------------------------------ | --------------------- | ------------------------ | ------------------------ | ------------------------------ | ----------------------------------- | ------------------ | ------------------------ | | ------------------------------------------------------------------------------------------ | --------------------- | ------------------------ | ------------------------ | ------------------------------ | ----------------------------------- | ------------------ | ------------------------ |
| [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-cls.pt) | 224 | 66.6 | 87.0 | 12.9 | 0.31 | 2.7 | 4.3 | | [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-cls.pt) | 224 | 66.6 | 87.0 | 12.9 | 0.31 | 2.7 | 4.3 |
| [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-cls.pt) | 224 | 72.3 | 91.1 | 23.4 | 0.35 | 6.4 | 13.5 | | [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-cls.pt) | 224 | 72.3 | 91.1 | 23.4 | 0.35 | 6.4 | 13.5 |
| [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-cls.pt) | 224 | 76.4 | 93.2 | 85.4 | 0.62 | 17.0 | 42.7 | | [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-cls.pt) | 224 | 76.4 | 93.2 | 85.4 | 0.62 | 17.0 | 42.7 |
| [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-cls.pt) | 224 | 78.0 | 94.1 | 163.0 | 0.87 | 37.5 | 99.7 | | [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-cls.pt) | 224 | 78.0 | 94.1 | 163.0 | 0.87 | 37.5 | 99.7 |
| [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-cls.pt) | 224 | 78.4 | 94.3 | 232.0 | 1.01 | 57.4 | 154.8 | | [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-cls.pt) | 224 | 78.4 | 94.3 | 232.0 | 1.01 | 57.4 | 154.8 |
=== "पोज (COCO)" === "पोज (COCO)"
@ -92,12 +92,12 @@ Yएक मॉडल के हर मानक, विशिष्ट कार
| मॉडल | आकार<br><sup>(पिक्स) | mAP<sup>शामिती<br>50-95 | mAP<sup>शामिती<br>50 | गति<br><sup>CPU ONNX<br>(ms) | गति<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(एम) | FLOPs<br><sup>(बी) | | मॉडल | आकार<br><sup>(पिक्स) | mAP<sup>शामिती<br>50-95 | mAP<sup>शामिती<br>50 | गति<br><sup>CPU ONNX<br>(ms) | गति<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(एम) | FLOPs<br><sup>(बी) |
| ----------------------------------------------------------------------------------------------------- | --------------------- | ------------------------ | -------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- | | ----------------------------------------------------------------------------------------------------- | --------------------- | ------------------------ | -------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
| [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 | | [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 |
| [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 | | [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 |
| [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 | | [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 |
| [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 | | [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 |
| [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 | | [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 |
| [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 | | [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 |
## उपयोग की उदाहरण ## उपयोग की उदाहरण

10
docs/hi/tasks/classify.md
View File

@ -24,11 +24,11 @@ keywords: Ultralytics, YOLOv8, इमेज क्लासिफिकेशन
| मॉडेल | आकार<br><sup>(पिक्सेल) | तालिका<br><sup>शीर्ष 1 | तालिका<br><sup>शीर्ष 5 | स्पीड<br><sup>सीपीयू ONNX<br>(मि. सेकंड) | स्पीड<br><sup>A100 TensorRT<br>(मि. सेकंड) | पैरामीटर<br><sup>(M) | FLOPs<br><sup>(B) at 640 | | मॉडेल | आकार<br><sup>(पिक्सेल) | तालिका<br><sup>शीर्ष 1 | तालिका<br><sup>शीर्ष 5 | स्पीड<br><sup>सीपीयू ONNX<br>(मि. सेकंड) | स्पीड<br><sup>A100 TensorRT<br>(मि. सेकंड) | पैरामीटर<br><sup>(M) | FLOPs<br><sup>(B) at 640 |
|----------------------------------------------------------------------------------------------|------------------------|------------------------|------------------------|------------------------------------------|--------------------------------------------|----------------------|--------------------------| |----------------------------------------------------------------------------------------------|------------------------|------------------------|------------------------|------------------------------------------|--------------------------------------------|----------------------|--------------------------|
| [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-cls.pt) | 224 | 66.6 | 87.0 | 12.9 | 0.31 | 2.7 | 4.3 | | [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-cls.pt) | 224 | 66.6 | 87.0 | 12.9 | 0.31 | 2.7 | 4.3 |
| [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-cls.pt) | 224 | 72.3 | 91.1 | 23.4 | 0.35 | 6.4 | 13.5 | | [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-cls.pt) | 224 | 72.3 | 91.1 | 23.4 | 0.35 | 6.4 | 13.5 |
| [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-cls.pt) | 224 | 76.4 | 93.2 | 85.4 | 0.62 | 17.0 | 42.7 | | [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-cls.pt) | 224 | 76.4 | 93.2 | 85.4 | 0.62 | 17.0 | 42.7 |
| [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-cls.pt) | 224 | 78.0 | 94.1 | 163.0 | 0.87 | 37.5 | 99.7 | | [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-cls.pt) | 224 | 78.0 | 94.1 | 163.0 | 0.87 | 37.5 | 99.7 |
| [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-cls.pt) | 224 | 78.4 | 94.3 | 232.0 | 1.01 | 57.4 | 154.8 | | [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-cls.pt) | 224 | 78.4 | 94.3 | 232.0 | 1.01 | 57.4 | 154.8 |
- **तालिका** मॉडेलों की ImageNet डेटासेट मान्यीकरण सेट पर सटीकता है। - **तालिका** मॉडेलों की ImageNet डेटासेट मान्यीकरण सेट पर सटीकता है।
<br>`yolo val classify data=path/to/ImageNet device=0` द्वारा पुनः उत्पन्न करें <br>`yolo val classify data=path/to/ImageNet device=0` द्वारा पुनः उत्पन्न करें

10
docs/hi/tasks/detect.md
View File

@ -36,11 +36,11 @@ YOLOv8 पूर्व प्रशिक्षित Detect मॉडल यह
| मॉडल | साइज़<br><sup>(pixels) | mAP<sup>val<br>50-95 | स्पीड<sup>CPU ONNX<br>(ms) | स्पीड<sup>A100 TensorRT<br>(ms) | पैराम्स<br><sup>(M) | FLOPs<br><sup>(B) | | मॉडल | साइज़<br><sup>(pixels) | mAP<sup>val<br>50-95 | स्पीड<sup>CPU ONNX<br>(ms) | स्पीड<sup>A100 TensorRT<br>(ms) | पैराम्स<br><sup>(M) | FLOPs<br><sup>(B) |
|--------------------------------------------------------------------------------------|------------------------|----------------------|----------------------------|---------------------------------|---------------------|-------------------| |--------------------------------------------------------------------------------------|------------------------|----------------------|----------------------------|---------------------------------|---------------------|-------------------|
| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 | | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 |
| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 | | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 |
| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 | | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 |
| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 | | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 |
| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 | | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 |
- **mAP<sup>val</sup>** मान को [COCO val2017](http://cocodataset.org) डेटासेट पर सिंगल-मॉडेल सिंगल-स्केल के लिए है। - **mAP<sup>val</sup>** मान को [COCO val2017](http://cocodataset.org) डेटासेट पर सिंगल-मॉडेल सिंगल-स्केल के लिए है।
<br>`yolo` द्वारा पुनः उत्पन्न करें `के द्वारा विन्यास करें yolo val data=coco.yaml device=0` <br>`yolo` द्वारा पुनः उत्पन्न करें `के द्वारा विन्यास करें yolo val data=coco.yaml device=0`

12
docs/hi/tasks/pose.md
View File

@ -35,12 +35,12 @@ YOLOv8 पूर्वानुमानित पोज मॉडलस यह
| मॉडल | आकार<br><sup>(तत्व) | mAP<sup>पोज<br>50-95 | mAP<sup>पोज<br>50 | ह्वेग<br><sup>CPU ONNX<br>(ms) | ह्वेग<br><sup>A100 TensorRT<br>(ms) | पैराम्स<br><sup>(M) | FLOPs<br><sup>(B) | | मॉडल | आकार<br><sup>(तत्व) | mAP<sup>पोज<br>50-95 | mAP<sup>पोज<br>50 | ह्वेग<br><sup>CPU ONNX<br>(ms) | ह्वेग<br><sup>A100 TensorRT<br>(ms) | पैराम्स<br><sup>(M) | FLOPs<br><sup>(B) |
|------------------------------------------------------------------------------------------------------|---------------------|----------------------|-------------------|--------------------------------|-------------------------------------|---------------------|-------------------| |------------------------------------------------------------------------------------------------------|---------------------|----------------------|-------------------|--------------------------------|-------------------------------------|---------------------|-------------------|
| [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 | | [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 |
| [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 | | [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 |
| [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 | | [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 |
| [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 | | [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 |
| [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 | | [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 |
| [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 | | [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 |
- **mAP<sup>val</sup>** मान एकल मॉडल एकल स्केल पर [COCO कीपॉइंट val2017](http://cocodataset.org) डेटासेट पर है। - **mAP<sup>val</sup>** मान एकल मॉडल एकल स्केल पर [COCO कीपॉइंट val2017](http://cocodataset.org) डेटासेट पर है।
<br>`yolo val pose data=coco-pose.yaml device=0` के द्वारा पुनरोत्पादित करें <br>`yolo val pose data=coco-pose.yaml device=0` के द्वारा पुनरोत्पादित करें

10
docs/hi/tasks/segment.md
View File

@ -33,11 +33,11 @@ YOLOv8 पूर्व प्रशिक्षित Segment मॉडल य
| मॉडल | आकार<br><sup>(पिक्सेल) | mAP<sup>बॉक्स<br>50-95 | mAP<sup>मास्क<br>50-95 | स्पीड<br><sup>CPU ONNX<br>(मि.सेकंड) | स्पीड<br><sup>A100 TensorRT<br>(मि.सेकंड) | पैराम्स<br><sup>(M) | FLOPs<br><sup>(B) | | मॉडल | आकार<br><sup>(पिक्सेल) | mAP<sup>बॉक्स<br>50-95 | mAP<sup>मास्क<br>50-95 | स्पीड<br><sup>CPU ONNX<br>(मि.सेकंड) | स्पीड<br><sup>A100 TensorRT<br>(मि.सेकंड) | पैराम्स<br><sup>(M) | FLOPs<br><sup>(B) |
|----------------------------------------------------------------------------------------------|------------------------|------------------------|------------------------|--------------------------------------|-------------------------------------------|---------------------|-------------------| |----------------------------------------------------------------------------------------------|------------------------|------------------------|------------------------|--------------------------------------|-------------------------------------------|---------------------|-------------------|
| [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 | | [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 |
| [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 | | [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 |
| [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 | | [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 |
| [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 | | [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 |
| [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 | | [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 |
- **mAP<sup>val</sup>** मान एकल मॉडल एकल स्केल के लिए [COCO val2017](http://cocodataset.org) डेटासेट पर होते हैं। - **mAP<sup>val</sup>** मान एकल मॉडल एकल स्केल के लिए [COCO val2017](http://cocodataset.org) डेटासेट पर होते हैं।
<br>`yolo val segment data=coco.yaml device=0` के द्वारा पुनर्जीवित किए जाएं। <br>`yolo val segment data=coco.yaml device=0` के द्वारा पुनर्जीवित किए जाएं।

6
docs/ja/models/yolo-nas.md
View File

@ -92,9 +92,9 @@ YOLO-NASモデルは、Small（s）、Medium（m）、Large（l）の3つのバ
| モデルの種類 | 事前学習済みの重み | サポートされるタスク | 推論 | 検証 | トレーニング | エクスポート | | モデルの種類 | 事前学習済みの重み | サポートされるタスク | 推論 | 検証 | トレーニング | エクスポート |
|------------|-----------------------------------------------------------------------------------------------|----------------------------|----|----|--------|--------| |------------|-----------------------------------------------------------------------------------------------|----------------------------|----|----|--------|--------|
| YOLO-NAS-s | [yolo_nas_s.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolo_nas_s.pt) | [物体検出](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ | | YOLO-NAS-s | [yolo_nas_s.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolo_nas_s.pt) | [物体検出](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ |
| YOLO-NAS-m | [yolo_nas_m.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolo_nas_m.pt) | [物体検出](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ | | YOLO-NAS-m | [yolo_nas_m.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolo_nas_m.pt) | [物体検出](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ |
| YOLO-NAS-l | [yolo_nas_l.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolo_nas_l.pt) | [物体検出](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ | | YOLO-NAS-l | [yolo_nas_l.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolo_nas_l.pt) | [物体検出](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ |
## 引用と謝辞 ## 引用と謝辞

20
docs/ja/models/yolov5.md
View File

@ -40,17 +40,17 @@ YOLOv5uは、物体検出方法論の進歩を表しています。Ultralytics
| モデル | YAML | サイズ<br><sup>(pixels) | mAP<sup>val<br>50-95 | 速度<br><sup>CPU ONNX<br>(ms) | 速度<br><sup>A100 TensorRT<br>(ms) | パラメータ<br><sup>(M) | FLOPS<br><sup>(B) | | モデル | YAML | サイズ<br><sup>(pixels) | mAP<sup>val<br>50-95 | 速度<br><sup>CPU ONNX<br>(ms) | 速度<br><sup>A100 TensorRT<br>(ms) | パラメータ<br><sup>(M) | FLOPS<br><sup>(B) |
|-------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------|-----------------------|----------------------|----------------------------|-------------------------------------|----------------------|-------------------| |-------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------|-----------------------|----------------------|----------------------------|-------------------------------------|----------------------|-------------------|
| [yolov5nu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5nu.pt) | [yolov5n.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 34.3 | 73.6 | 1.06 | 2.6 | 7.7 | | [yolov5nu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5nu.pt) | [yolov5n.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 34.3 | 73.6 | 1.06 | 2.6 | 7.7 |
| [yolov5su.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5su.pt) | [yolov5s.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 43.0 | 120.7 | 1.27 | 9.1 | 24.0 | | [yolov5su.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5su.pt) | [yolov5s.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 43.0 | 120.7 | 1.27 | 9.1 | 24.0 |
| [yolov5mu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5mu.pt) | [yolov5m.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 49.0 | 233.9 | 1.86 | 25.1 | 64.2 | | [yolov5mu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5mu.pt) | [yolov5m.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 49.0 | 233.9 | 1.86 | 25.1 | 64.2 |
| [yolov5lu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5lu.pt) | [yolov5l.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 52.2 | 408.4 | 2.50 | 53.2 | 135.0 | | [yolov5lu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5lu.pt) | [yolov5l.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 52.2 | 408.4 | 2.50 | 53.2 | 135.0 |
| [yolov5xu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5xu.pt) | [yolov5x.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 53.2 | 763.2 | 3.81 | 97.2 | 246.4 | | [yolov5xu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5xu.pt) | [yolov5x.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 53.2 | 763.2 | 3.81 | 97.2 | 246.4 |
| | | | | | | | | | | | | | | | | |
| [yolov5n6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5n6u.pt) | [yolov5n6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 42.1 | 211.0 | 1.83 | 4.3 | 7.8 | | [yolov5n6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5n6u.pt) | [yolov5n6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 42.1 | 211.0 | 1.83 | 4.3 | 7.8 |
| [yolov5s6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5s6u.pt) | [yolov5s6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 48.6 | 422.6 | 2.34 | 15.3 | 24.6 | | [yolov5s6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5s6u.pt) | [yolov5s6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 48.6 | 422.6 | 2.34 | 15.3 | 24.6 |
| [yolov5m6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5m6u.pt) | [yolov5m6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 53.6 | 810.9 | 4.36 | 41.2 | 65.7 | | [yolov5m6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5m6u.pt) | [yolov5m6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 53.6 | 810.9 | 4.36 | 41.2 | 65.7 |
| [yolov5l6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5l6u.pt) | [yolov5l6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 55.7 | 1470.9 | 5.47 | 86.1 | 137.4 | | [yolov5l6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5l6u.pt) | [yolov5l6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 55.7 | 1470.9 | 5.47 | 86.1 | 137.4 |
| [yolov5x6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5x6u.pt) | [yolov5x6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 56.8 | 2436.5 | 8.98 | 155.4 | 250.7 | | [yolov5x6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5x6u.pt) | [yolov5x6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 56.8 | 2436.5 | 8.98 | 155.4 | 250.7 |
## 使用例 ## 使用例

52
docs/ja/models/yolov8.md
View File

@ -44,11 +44,11 @@ YOLOv8シリーズの各バリアントは、それぞれのタスクに最適
| モデル | サイズ（ピクセル） | mAP<sup>val<br>50-95 | スピード（CPU ONNX<br>（ミリ秒）） | スピード（A100 TensorRT<br>（ミリ秒）） | パラメータ数（百万） | FLOPs（10億） | | モデル | サイズ（ピクセル） | mAP<sup>val<br>50-95 | スピード（CPU ONNX<br>（ミリ秒）） | スピード（A100 TensorRT<br>（ミリ秒）） | パラメータ数（百万） | FLOPs（10億） |
| ------------------------------------------------------------------------------------ | --------------------- | -------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- | | ------------------------------------------------------------------------------------ | --------------------- | -------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 | | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 |
| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 | | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 |
| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 | | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 |
| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 | | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 |
| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 | | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 |
=== "検出（Open Images V7）" === "検出（Open Images V7）"
@ -56,11 +56,11 @@ YOLOv8シリーズの各バリアントは、それぞれのタスクに最適
| モデル | サイズ（ピクセル） | mAP<sup>val<br>50-95 | スピード（CPU ONNX<br>（ミリ秒）） | スピード（A100 TensorRT<br>（ミリ秒）） | パラメータ数（百万） | FLOPs（10億） | | モデル | サイズ（ピクセル） | mAP<sup>val<br>50-95 | スピード（CPU ONNX<br>（ミリ秒）） | スピード（A100 TensorRT<br>（ミリ秒）） | パラメータ数（百万） | FLOPs（10億） |
| ----------------------------------------------------------------------------------------- | --------------------- | -------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- | | ----------------------------------------------------------------------------------------- | --------------------- | -------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-oiv7.pt) | 640 | 18.4 | 142.4 | 1.21 | 3.5 | 10.5 | | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-oiv7.pt) | 640 | 18.4 | 142.4 | 1.21 | 3.5 | 10.5 |
| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-oiv7.pt) | 640 | 27.7 | 183.1 | 1.40 | 11.4 | 29.7 | | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-oiv7.pt) | 640 | 27.7 | 183.1 | 1.40 | 11.4 | 29.7 |
| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-oiv7.pt) | 640 | 33.6 | 408.5 | 2.26 | 26.2 | 80.6 | | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-oiv7.pt) | 640 | 33.6 | 408.5 | 2.26 | 26.2 | 80.6 |
| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-oiv7.pt) | 640 | 34.9 | 596.9 | 2.43 | 44.1 | 167.4 | | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-oiv7.pt) | 640 | 34.9 | 596.9 | 2.43 | 44.1 | 167.4 |
| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-oiv7.pt) | 640 | 36.3 | 860.6 | 3.56 | 68.7 | 260.6 | | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-oiv7.pt) | 640 | 36.3 | 860.6 | 3.56 | 68.7 | 260.6 |
=== "セグメンテーション（COCO）" === "セグメンテーション（COCO）"
@ -68,11 +68,11 @@ YOLOv8シリーズの各バリアントは、それぞれのタスクに最適
| モデル | サイズ（ピクセル） | mAP<sup>box<br>50-95 | mAP<sup>mask<br>50-95 | スピード（CPU ONNX<br>（ミリ秒）） | スピード（A100 TensorRT<br>（ミリ秒）） | パラメータ数（百万） | FLOPs（10億） | | モデル | サイズ（ピクセル） | mAP<sup>box<br>50-95 | mAP<sup>mask<br>50-95 | スピード（CPU ONNX<br>（ミリ秒）） | スピード（A100 TensorRT<br>（ミリ秒）） | パラメータ数（百万） | FLOPs（10億） |
| -------------------------------------------------------------------------------------------- | --------------------- | -------------------- | --------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- | | -------------------------------------------------------------------------------------------- | --------------------- | -------------------- | --------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
| [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 | | [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 |
| [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 | | [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 |
| [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 | | [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 |
| [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 | | [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 |
| [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 | | [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 |
=== "分類（ImageNet）" === "分類（ImageNet）"
@ -80,11 +80,11 @@ YOLOv8シリーズの各バリアントは、それぞれのタスクに最適
| モデル | サイズ（ピクセル） | top1精度 | top5精度 | スピード（CPU ONNX<br>（ミリ秒）） | スピード（A100 TensorRT<br>（ミリ秒）） | パラメータ数（百万） | FLOPs（640ピクセル時の10億） | | モデル | サイズ（ピクセル） | top1精度 | top5精度 | スピード（CPU ONNX<br>（ミリ秒）） | スピード（A100 TensorRT<br>（ミリ秒）） | パラメータ数（百万） | FLOPs（640ピクセル時の10億） |
| -------------------------------------------------------------------------------------------- | --------------------- | --------- | --------- | ------------------------------ | ----------------------------------- | ------------------ | ------------------------ | | -------------------------------------------------------------------------------------------- | --------------------- | --------- | --------- | ------------------------------ | ----------------------------------- | ------------------ | ------------------------ |
| [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-cls.pt) | 224 | 66.6 | 87.0 | 12.9 | 0.31 | 2.7 | 4.3 | | [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-cls.pt) | 224 | 66.6 | 87.0 | 12.9 | 0.31 | 2.7 | 4.3 |
| [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-cls.pt) | 224 | 72.3 | 91.1 | 23.4 | 0.35 | 6.4 | 13.5 | | [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-cls.pt) | 224 | 72.3 | 91.1 | 23.4 | 0.35 | 6.4 | 13.5 |
| [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-cls.pt) | 224 | 76.4 | 93.2 | 85.4 | 0.62 | 17.0 | 42.7 | | [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-cls.pt) | 224 | 76.4 | 93.2 | 85.4 | 0.62 | 17.0 | 42.7 |
| [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-cls.pt) | 224 | 78.0 | 94.1 | 163.0 | 0.87 | 37.5 | 99.7 | | [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-cls.pt) | 224 | 78.0 | 94.1 | 163.0 | 0.87 | 37.5 | 99.7 |
| [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-cls.pt) | 224 | 78.4 | 94.3 | 232.0 | 1.01 | 57.4 | 154.8 | | [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-cls.pt) | 224 | 78.4 | 94.3 | 232.0 | 1.01 | 57.4 | 154.8 |
=== "ポーズ（COCO）" === "ポーズ（COCO）"
@ -92,12 +92,12 @@ YOLOv8シリーズの各バリアントは、それぞれのタスクに最適
| モデル | サイズ（ピクセル） | mAP<sup>pose<br>50-95 | mAP<sup>pose<br>50 | スピード（CPU ONNX<br>（ミリ秒）） | スピード（A100 TensorRT<br>（ミリ秒）） | パラメータ数（百万） | FLOPs（10億） | | モデル | サイズ（ピクセル） | mAP<sup>pose<br>50-95 | mAP<sup>pose<br>50 | スピード（CPU ONNX<br>（ミリ秒）） | スピード（A100 TensorRT<br>（ミリ秒）） | パラメータ数（百万） | FLOPs（10億） |
| ---------------------------------------------------------------------------------------------------- | --------------------- | --------------------- | ------------------ | ------------------------------ | ----------------------------------- | ------------------ | ----------------- | | ---------------------------------------------------------------------------------------------------- | --------------------- | --------------------- | ------------------ | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
| [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 | | [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 |
| [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 | | [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 |
| [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 | | [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 |
| [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 | | [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 |
| [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 | | [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 |
| [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 | | [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 |
## 使用例 ## 使用例

10
docs/ja/tasks/classify.md
View File

@ -24,11 +24,11 @@ keywords: Ultralytics, YOLOv8, 画像分類, 事前トレーニングされた
| モデル | サイズ<br><sup>(ピクセル) | 正確性<br><sup>トップ1 | 正確性<br><sup>トップ5 | スピード<br><sup>CPU ONNX<br>(ms) | スピード<br><sup>A100 TensorRT<br>(ms) | パラメータ<br><sup>(M) | FLOPs<br><sup>(B) at 640 | | モデル | サイズ<br><sup>(ピクセル) | 正確性<br><sup>トップ1 | 正確性<br><sup>トップ5 | スピード<br><sup>CPU ONNX<br>(ms) | スピード<br><sup>A100 TensorRT<br>(ms) | パラメータ<br><sup>(M) | FLOPs<br><sup>(B) at 640 |
|----------------------------------------------------------------------------------------------|--------------------|------------------|------------------|-------------------------------|------------------------------------|-------------------|--------------------------| |----------------------------------------------------------------------------------------------|--------------------|------------------|------------------|-------------------------------|------------------------------------|-------------------|--------------------------|
| [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-cls.pt) | 224 | 66.6 | 87.0 | 12.9 | 0.31 | 2.7 | 4.3 | | [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-cls.pt) | 224 | 66.6 | 87.0 | 12.9 | 0.31 | 2.7 | 4.3 |
| [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-cls.pt) | 224 | 72.3 | 91.1 | 23.4 | 0.35 | 6.4 | 13.5 | | [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-cls.pt) | 224 | 72.3 | 91.1 | 23.4 | 0.35 | 6.4 | 13.5 |
| [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-cls.pt) | 224 | 76.4 | 93.2 | 85.4 | 0.62 | 17.0 | 42.7 | | [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-cls.pt) | 224 | 76.4 | 93.2 | 85.4 | 0.62 | 17.0 | 42.7 |
| [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-cls.pt) | 224 | 78.0 | 94.1 | 163.0 | 0.87 | 37.5 | 99.7 | | [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-cls.pt) | 224 | 78.0 | 94.1 | 163.0 | 0.87 | 37.5 | 99.7 |
| [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-cls.pt) | 224 | 78.4 | 94.3 | 232.0 | 1.01 | 57.4 | 154.8 | | [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-cls.pt) | 224 | 78.4 | 94.3 | 232.0 | 1.01 | 57.4 | 154.8 |
- **正確性** の値は [ImageNet](https://www.image-net.org/) データセットの検証セットでのモデルの正確性です。 - **正確性** の値は [ImageNet](https://www.image-net.org/) データセットの検証セットでのモデルの正確性です。
<br>再現するには `yolo val classify data=path/to/ImageNet device=0` <br>再現するには `yolo val classify data=path/to/ImageNet device=0`

10
docs/ja/tasks/detect.md
View File

@ -35,11 +35,11 @@ keywords: YOLOv8, Ultralytics, 物体検出, 事前訓練済みモデル, トレ
| モデル | サイズ<br><sup>(ピクセル) | mAP<sup>val<br>50-95 | 速度<br><sup>CPU ONNX<br>(ms) | 速度<br><sup>A100 TensorRT<br>(ms) | パラメータ数<br><sup>(M) | FLOPs<br><sup>(B) | | モデル | サイズ<br><sup>(ピクセル) | mAP<sup>val<br>50-95 | 速度<br><sup>CPU ONNX<br>(ms) | 速度<br><sup>A100 TensorRT<br>(ms) | パラメータ数<br><sup>(M) | FLOPs<br><sup>(B) |
|--------------------------------------------------------------------------------------|--------------------|----------------------|-----------------------------|----------------------------------|--------------------|-------------------| |--------------------------------------------------------------------------------------|--------------------|----------------------|-----------------------------|----------------------------------|--------------------|-------------------|
| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 | | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 |
| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 | | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 |
| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 | | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 |
| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 | | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 |
| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 | | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 |
- **mAP<sup>val</sup>** の値は[COCO val2017](http://cocodataset.org)データセットにおいて、単一モデル単一スケールでのものです。 - **mAP<sup>val</sup>** の値は[COCO val2017](http://cocodataset.org)データセットにおいて、単一モデル単一スケールでのものです。
<br>再現方法: `yolo val detect data=coco.yaml device=0` <br>再現方法: `yolo val detect data=coco.yaml device=0`

12
docs/ja/tasks/pose.md
View File

@ -35,12 +35,12 @@ YOLOv8事前トレーニング済みポーズモデルはこちらです。Detec
| モデル | サイズ<br><sup>(ピクセル) | mAP<sup>ポーズ<br>50-95 | mAP<sup>ポーズ<br>50 | 速度<br><sup>CPU ONNX<br>(ミリ秒) | 速度<br><sup>A100 TensorRT<br>(ミリ秒) | パラメータ<br><sup>(M) | FLOPs<br><sup>(B) | | モデル | サイズ<br><sup>(ピクセル) | mAP<sup>ポーズ<br>50-95 | mAP<sup>ポーズ<br>50 | 速度<br><sup>CPU ONNX<br>(ミリ秒) | 速度<br><sup>A100 TensorRT<br>(ミリ秒) | パラメータ<br><sup>(M) | FLOPs<br><sup>(B) |
|------------------------------------------------------------------------------------------------------|--------------------|----------------------|-------------------|------------------------------|-----------------------------------|-------------------|-------------------| |------------------------------------------------------------------------------------------------------|--------------------|----------------------|-------------------|------------------------------|-----------------------------------|-------------------|-------------------|
| [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 | | [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 |
| [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 | | [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 |
| [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 | | [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 |
| [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 | | [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 |
| [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 | | [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 |
| [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 | | [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 |
- **mAP<sup>val</sup>** の値は、[COCO Keypoints val2017](http://cocodataset.org)データセットでの単一モデル単一スケールに対するものです。 - **mAP<sup>val</sup>** の値は、[COCO Keypoints val2017](http://cocodataset.org)データセットでの単一モデル単一スケールに対するものです。
<br>再現方法 `yolo val pose data=coco-pose.yaml device=0` <br>再現方法 `yolo val pose data=coco-pose.yaml device=0`

10
docs/ja/tasks/segment.md
View File

@ -35,11 +35,11 @@ keywords: yolov8, インスタンスセグメンテーション, Ultralytics, CO
| モデル | サイズ<br><sup>(ピクセル) | mAP<sup>box<br>50-95 | mAP<sup>mask<br>50-95 | スピード<br><sup>CPU ONNX<br>(ms) | スピード<br><sup>A100 TensorRT<br>(ms) | パラメータ<br><sup>(M) | FLOPs<br><sup>(B) | | モデル | サイズ<br><sup>(ピクセル) | mAP<sup>box<br>50-95 | mAP<sup>mask<br>50-95 | スピード<br><sup>CPU ONNX<br>(ms) | スピード<br><sup>A100 TensorRT<br>(ms) | パラメータ<br><sup>(M) | FLOPs<br><sup>(B) |
|----------------------------------------------------------------------------------------------|--------------------|----------------------|-----------------------|-------------------------------|------------------------------------|-------------------|-------------------| |----------------------------------------------------------------------------------------------|--------------------|----------------------|-----------------------|-------------------------------|------------------------------------|-------------------|-------------------|
| [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 | | [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 |
| [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 | | [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 |
| [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 | | [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 |
| [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 | | [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 |
| [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 | | [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 |
- **mAP<sup>val</sup>**の値は[COCO val2017](http://cocodataset.org)データセットでの単一モデル単一スケールの値です。 - **mAP<sup>val</sup>**の値は[COCO val2017](http://cocodataset.org)データセットでの単一モデル単一スケールの値です。
<br>再現するには `yolo val segment data=coco.yaml device=0` <br>再現するには `yolo val segment data=coco.yaml device=0`

6
docs/ko/models/yolo-nas.md
View File

@ -92,9 +92,9 @@ YOLO-NAS 모델은 Small (s), Medium (m) 및 Large (l) 세 가지 변형이 있
| 모델 유형 | 사전 훈련된 가중치 | 지원되는 작업 | 추론 | 유효성 검사 | 훈련 | 내보내기 | | 모델 유형 | 사전 훈련된 가중치 | 지원되는 작업 | 추론 | 유효성 검사 | 훈련 | 내보내기 |
|------------|-----------------------------------------------------------------------------------------------|-----------------------------|----|--------|----|------| |------------|-----------------------------------------------------------------------------------------------|-----------------------------|----|--------|----|------|
| YOLO-NAS-s | [yolo_nas_s.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolo_nas_s.pt) | [물체 감지](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ | | YOLO-NAS-s | [yolo_nas_s.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolo_nas_s.pt) | [물체 감지](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ |
| YOLO-NAS-m | [yolo_nas_m.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolo_nas_m.pt) | [물체 감지](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ | | YOLO-NAS-m | [yolo_nas_m.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolo_nas_m.pt) | [물체 감지](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ |
| YOLO-NAS-l | [yolo_nas_l.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolo_nas_l.pt) | [물체 감지](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ | | YOLO-NAS-l | [yolo_nas_l.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolo_nas_l.pt) | [물체 감지](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ |
## 인용 및 감사의 말씀 ## 인용 및 감사의 말씀

20
docs/ko/models/yolov5.md
View File

@ -40,17 +40,17 @@ YOLOv5u는 객체 감지 기법에서의 진보를 나타냅니다. Ultralytics
| 모델 | YAML | 크기<br><sup>(픽셀) | mAP<sup>val<br>50-95 | 속도<br><sup>CPU ONNX<br>(ms) | 속도<br><sup>A100 TensorRT<br>(ms) | 매개변수<br><sup>(M) | FLOPs<br><sup>(B) | | 모델 | YAML | 크기<br><sup>(픽셀) | mAP<sup>val<br>50-95 | 속도<br><sup>CPU ONNX<br>(ms) | 속도<br><sup>A100 TensorRT<br>(ms) | 매개변수<br><sup>(M) | FLOPs<br><sup>(B) |
|---------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------|-----------------------|----------------------|--------------------------------|-------------------------------------|--------------------|-------------------| |---------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------|-----------------------|----------------------|--------------------------------|-------------------------------------|--------------------|-------------------|
| [yolov5nu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5nu.pt) | [yolov5n.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 34.3 | 73.6 | 1.06 | 2.6 | 7.7 | | [yolov5nu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5nu.pt) | [yolov5n.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 34.3 | 73.6 | 1.06 | 2.6 | 7.7 |
| [yolov5su.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5su.pt) | [yolov5s.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 43.0 | 120.7 | 1.27 | 9.1 | 24.0 | | [yolov5su.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5su.pt) | [yolov5s.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 43.0 | 120.7 | 1.27 | 9.1 | 24.0 |
| [yolov5mu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5mu.pt) | [yolov5m.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 49.0 | 233.9 | 1.86 | 25.1 | 64.2 | | [yolov5mu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5mu.pt) | [yolov5m.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 49.0 | 233.9 | 1.86 | 25.1 | 64.2 |
| [yolov5lu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5lu.pt) | [yolov5l.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 52.2 | 408.4 | 2.50 | 53.2 | 135.0 | | [yolov5lu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5lu.pt) | [yolov5l.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 52.2 | 408.4 | 2.50 | 53.2 | 135.0 |
| [yolov5xu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5xu.pt) | [yolov5x.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 53.2 | 763.2 | 3.81 | 97.2 | 246.4 | | [yolov5xu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5xu.pt) | [yolov5x.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 53.2 | 763.2 | 3.81 | 97.2 | 246.4 |
| | | | | | | | | | | | | | | | | |
| [yolov5n6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5n6u.pt) | [yolov5n6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 42.1 | 211.0 | 1.83 | 4.3 | 7.8 | | [yolov5n6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5n6u.pt) | [yolov5n6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 42.1 | 211.0 | 1.83 | 4.3 | 7.8 |
| [yolov5s6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5s6u.pt) | [yolov5s6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 48.6 | 422.6 | 2.34 | 15.3 | 24.6 | | [yolov5s6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5s6u.pt) | [yolov5s6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 48.6 | 422.6 | 2.34 | 15.3 | 24.6 |
| [yolov5m6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5m6u.pt) | [yolov5m6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 53.6 | 810.9 | 4.36 | 41.2 | 65.7 | | [yolov5m6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5m6u.pt) | [yolov5m6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 53.6 | 810.9 | 4.36 | 41.2 | 65.7 |
| [yolov5l6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5l6u.pt) | [yolov5l6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 55.7 | 1470.9 | 5.47 | 86.1 | 137.4 | | [yolov5l6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5l6u.pt) | [yolov5l6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 55.7 | 1470.9 | 5.47 | 86.1 | 137.4 |
| [yolov5x6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5x6u.pt) | [yolov5x6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 56.8 | 2436.5 | 8.98 | 155.4 | 250.7 | | [yolov5x6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5x6u.pt) | [yolov5x6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 56.8 | 2436.5 | 8.98 | 155.4 | 250.7 |
## 사용 예제 ## 사용 예제

52
docs/ko/models/yolov8.md
View File

@ -44,11 +44,11 @@ YOLOv8 시리즈는 컴퓨터 비전의 특정 작업을 위해 특화된 다양
| 모델 | 크기<br><sup>(픽셀) | mAP<br>val 50-95 | 속도<br><sup>CPU ONNX<br>(밀리초) | 속도<br><sup>A100 TensorRT<br>(밀리초) | 매개변수<br><sup>(백만) | FLOPs<br><sup>(십억) | | 모델 | 크기<br><sup>(픽셀) | mAP<br>val 50-95 | 속도<br><sup>CPU ONNX<br>(밀리초) | 속도<br><sup>A100 TensorRT<br>(밀리초) | 매개변수<br><sup>(백만) | FLOPs<br><sup>(십억) |
| ------------------------------------------------------------------------------------ | --------------------- | -------------------- | ------------------------------ | ----------------------------------- | ------------------- | ----------------- | | ------------------------------------------------------------------------------------ | --------------------- | -------------------- | ------------------------------ | ----------------------------------- | ------------------- | ----------------- |
| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 | | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 |
| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 | | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 |
| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 | | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 |
| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 | | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 |
| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 | | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 |
=== "객체 탐지 (Open Images V7)" === "객체 탐지 (Open Images V7)"
@ -56,11 +56,11 @@ YOLOv8 시리즈는 컴퓨터 비전의 특정 작업을 위해 특화된 다양
| 모델 | 크기<br><sup>(픽셀) | mAP<br>val 50-95 | 속도<br><sup>CPU ONNX<br>(밀리초) | 속도<br><sup>A100 TensorRT<br>(밀리초) | 매개변수<br><sup>(백만) | FLOPs<br><sup>(십억) | | 모델 | 크기<br><sup>(픽셀) | mAP<br>val 50-95 | 속도<br><sup>CPU ONNX<br>(밀리초) | 속도<br><sup>A100 TensorRT<br>(밀리초) | 매개변수<br><sup>(백만) | FLOPs<br><sup>(십억) |
| ----------------------------------------------------------------------------------------- | --------------------- | -------------------- | ------------------------------ | ----------------------------------- | ------------------- | ----------------- | | ----------------------------------------------------------------------------------------- | --------------------- | -------------------- | ------------------------------ | ----------------------------------- | ------------------- | ----------------- |
| [YOLOv8n-oiv7](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-oiv7.pt) | 640 | 18.4 | 142.4 | 1.21 | 3.5 | 10.5 | | [YOLOv8n-oiv7](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-oiv7.pt) | 640 | 18.4 | 142.4 | 1.21 | 3.5 | 10.5 |
| [YOLOv8s-oiv7](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-oiv7.pt) | 640 | 27.7 | 183.1 | 1.40 | 11.4 | 29.7 | | [YOLOv8s-oiv7](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-oiv7.pt) | 640 | 27.7 | 183.1 | 1.40 | 11.4 | 29.7 |
| [YOLOv8m-oiv7](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-oiv7.pt) | 640 | 33.6 | 408.5 | 2.26 | 26.2 | 80.6 | | [YOLOv8m-oiv7](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-oiv7.pt) | 640 | 33.6 | 408.5 | 2.26 | 26.2 | 80.6 |
| [YOLOv8l-oiv7](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-oiv7.pt) | 640 | 34.9 | 596.9 | 2.43 | 44.1 | 167.4 | | [YOLOv8l-oiv7](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-oiv7.pt) | 640 | 34.9 | 596.9 | 2.43 | 44.1 | 167.4 |
| [YOLOv8x-oiv7](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-oiv7.pt) | 640 | 36.3 | 860.6 | 3.56 | 68.7 | 260.6 | | [YOLOv8x-oiv7](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-oiv7.pt) | 640 | 36.3 | 860.6 | 3.56 | 68.7 | 260.6 |
=== "세그멘테이션 (COCO)" === "세그멘테이션 (COCO)"
@ -68,11 +68,11 @@ YOLOv8 시리즈는 컴퓨터 비전의 특정 작업을 위해 특화된 다양
| 모델 | 크기<br><sup>(픽셀) | mAP<br>box 50-95 | mAP<br>mask 50-95 | 속도<br><sup>CPU ONNX<br>(밀리초) | 속도<br><sup>A100 TensorRT<br>(밀리초) | 매개변수<br><sup>(백만) | FLOPs<br><sup>(십억) | | 모델 | 크기<br><sup>(픽셀) | mAP<br>box 50-95 | mAP<br>mask 50-95 | 속도<br><sup>CPU ONNX<br>(밀리초) | 속도<br><sup>A100 TensorRT<br>(밀리초) | 매개변수<br><sup>(백만) | FLOPs<br><sup>(십억) |
| -------------------------------------------------------------------------------------------- | --------------------- | -------------------- | ------------------ | ------------------------------ | ----------------------------------- | ------------------- | ----------------- | | -------------------------------------------------------------------------------------------- | --------------------- | -------------------- | ------------------ | ------------------------------ | ----------------------------------- | ------------------- | ----------------- |
| [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 | | [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 |
| [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 | | [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 |
| [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 | | [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 |
| [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 | | [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 |
| [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 | | [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 |
=== "분류 (ImageNet)" === "분류 (ImageNet)"
@ -80,11 +80,11 @@ YOLOv8 시리즈는 컴퓨터 비전의 특정 작업을 위해 특화된 다양
| 모델 | 크기<br><sup>(픽셀) | top1 정확도 | top5 정확도 | 속도<br><sup>CPU ONNX<br>(밀리초) | 속도<br><sup>A100 TensorRT<br>(밀리초) | 매개변수<br><sup>(백만) | FLOPs<br><sup>(백만) at 640 | | 모델 | 크기<br><sup>(픽셀) | top1 정확도 | top5 정확도 | 속도<br><sup>CPU ONNX<br>(밀리초) | 속도<br><sup>A100 TensorRT<br>(밀리초) | 매개변수<br><sup>(백만) | FLOPs<br><sup>(백만) at 640 |
| -------------------------------------------------------------------------------------------- | --------------------- | -------------------- | ----------------- | ------------------------------ | ----------------------------------- | ------------------- | ------------------------ | | -------------------------------------------------------------------------------------------- | --------------------- | -------------------- | ----------------- | ------------------------------ | ----------------------------------- | ------------------- | ------------------------ |
| [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-cls.pt) | 224 | 66.6 | 87.0 | 12.9 | 0.31 | 2.7 | 4.3 | | [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-cls.pt) | 224 | 66.6 | 87.0 | 12.9 | 0.31 | 2.7 | 4.3 |
| [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-cls.pt) | 224 | 72.3 | 91.1 | 23.4 | 0.35 | 6.4 | 13.5 | | [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-cls.pt) | 224 | 72.3 | 91.1 | 23.4 | 0.35 | 6.4 | 13.5 |
| [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-cls.pt) | 224 | 76.4 | 93.2 | 85.4 | 0.62 | 17.0 | 42.7 | | [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-cls.pt) | 224 | 76.4 | 93.2 | 85.4 | 0.62 | 17.0 | 42.7 |
| [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-cls.pt) | 224 | 78.0 | 94.1 | 163.0 | 0.87 | 37.5 | 99.7 | | [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-cls.pt) | 224 | 78.0 | 94.1 | 163.0 | 0.87 | 37.5 | 99.7 |
| [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-cls.pt) | 224 | 78.4 | 94.3 | 232.0 | 1.01 | 57.4 | 154.8 | | [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-cls.pt) | 224 | 78.4 | 94.3 | 232.0 | 1.01 | 57.4 | 154.8 |
=== "포즈 (COCO)" === "포즈 (COCO)"
@ -92,12 +92,12 @@ YOLOv8 시리즈는 컴퓨터 비전의 특정 작업을 위해 특화된 다양
| 모델 | 크기<br><sup>(픽셀) | mAP<br>pose 50-95 | mAP<br>pose 50 | 속도<br><sup>CPU ONNX<br>(밀리초) | 속도<br><sup>A100 TensorRT<br>(밀리초) | 매개변수<br><sup>(백만) | FLOPs<br><sup>(십억) | | 모델 | 크기<br><sup>(픽셀) | mAP<br>pose 50-95 | mAP<br>pose 50 | 속도<br><sup>CPU ONNX<br>(밀리초) | 속도<br><sup>A100 TensorRT<br>(밀리초) | 매개변수<br><sup>(백만) | FLOPs<br><sup>(십억) |
| ---------------------------------------------------------------------------------------------------- | --------------------- | -------------------- | ----------------- | ------------------------------ | ----------------------------------- | ------------------- | ----------------- | | ---------------------------------------------------------------------------------------------------- | --------------------- | -------------------- | ----------------- | ------------------------------ | ----------------------------------- | ------------------- | ----------------- |
| [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 | | [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 |
| [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 | | [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 |
| [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 | | [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 |
| [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 | | [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 |
| [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 | | [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 |
| [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 | | [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 |
## 사용 예제 ## 사용 예제

10
docs/ko/tasks/classify.md
View File

@ -24,11 +24,11 @@ keywords: Ultralytics, YOLOv8, 이미지 분류, 사전 훈련된 모델, YOLOv8
| 모델 | 크기<br><sup>(픽셀) | 정확도<br><sup>top1 | 정확도<br><sup>top5 | 속도<br><sup>CPU ONNX<br>(ms) | 속도<br><sup>A100 TensorRT<br>(ms) | 매개변수<br><sup>(M) | FLOPs<br><sup>(B) at 640 | | 모델 | 크기<br><sup>(픽셀) | 정확도<br><sup>top1 | 정확도<br><sup>top5 | 속도<br><sup>CPU ONNX<br>(ms) | 속도<br><sup>A100 TensorRT<br>(ms) | 매개변수<br><sup>(M) | FLOPs<br><sup>(B) at 640 |
|----------------------------------------------------------------------------------------------|-----------------|------------------|------------------|-----------------------------|----------------------------------|------------------|--------------------------| |----------------------------------------------------------------------------------------------|-----------------|------------------|------------------|-----------------------------|----------------------------------|------------------|--------------------------|
| [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-cls.pt) | 224 | 66.6 | 87.0 | 12.9 | 0.31 | 2.7 | 4.3 | | [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-cls.pt) | 224 | 66.6 | 87.0 | 12.9 | 0.31 | 2.7 | 4.3 |
| [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-cls.pt) | 224 | 72.3 | 91.1 | 23.4 | 0.35 | 6.4 | 13.5 | | [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-cls.pt) | 224 | 72.3 | 91.1 | 23.4 | 0.35 | 6.4 | 13.5 |
| [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-cls.pt) | 224 | 76.4 | 93.2 | 85.4 | 0.62 | 17.0 | 42.7 | | [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-cls.pt) | 224 | 76.4 | 93.2 | 85.4 | 0.62 | 17.0 | 42.7 |
| [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-cls.pt) | 224 | 78.0 | 94.1 | 163.0 | 0.87 | 37.5 | 99.7 | | [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-cls.pt) | 224 | 78.0 | 94.1 | 163.0 | 0.87 | 37.5 | 99.7 |
| [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-cls.pt) | 224 | 78.4 | 94.3 | 232.0 | 1.01 | 57.4 | 154.8 | | [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-cls.pt) | 224 | 78.4 | 94.3 | 232.0 | 1.01 | 57.4 | 154.8 |
- **정확도** 값은 [ImageNet](https://www.image-net.org/) 데이터셋 검증 세트에서의 모델 정확도입니다. - **정확도** 값은 [ImageNet](https://www.image-net.org/) 데이터셋 검증 세트에서의 모델 정확도입니다.
<br>[ImageNet](https://www.image-net.org/)에서 재현 가능합니다: `yolo val classify data=path/to/ImageNet device=0` <br>[ImageNet](https://www.image-net.org/)에서 재현 가능합니다: `yolo val classify data=path/to/ImageNet device=0`

10
docs/ko/tasks/detect.md
View File

@ -35,11 +35,11 @@ keywords: YOLOv8, Ultralytics, 객체 감지, 사전 훈련된 모델, 훈련,
| 모델 | 크기<br><sup>(픽셀) | mAP<sup>val<br>50-95 | 속도<br><sup>CPU ONNX<br>(ms) | 속도<br><sup>A100 TensorRT<br>(ms) | 파라미터<br><sup>(M) | FLOPs<br><sup>(B) | | 모델 | 크기<br><sup>(픽셀) | mAP<sup>val<br>50-95 | 속도<br><sup>CPU ONNX<br>(ms) | 속도<br><sup>A100 TensorRT<br>(ms) | 파라미터<br><sup>(M) | FLOPs<br><sup>(B) |
|--------------------------------------------------------------------------------------|-----------------|----------------------|-----------------------------|----------------------------------|------------------|-------------------| |--------------------------------------------------------------------------------------|-----------------|----------------------|-----------------------------|----------------------------------|------------------|-------------------|
| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 | | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 |
| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 | | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 |
| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 | | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 |
| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 | | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 |
| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 | | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 |
- **mAP<sup>val</sup>** 값은 [COCO val2017](http://cocodataset.org) 데이터셋에서 단일 모델 단일 스케일을 사용한 값입니다. - **mAP<sup>val</sup>** 값은 [COCO val2017](http://cocodataset.org) 데이터셋에서 단일 모델 단일 스케일을 사용한 값입니다.
<br>[COCO](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/datasets/coco.yaml) 데이터와 `yolo val detect data=coco.yaml device=0` 명령으로 재현할 수 있습니다. <br>[COCO](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/datasets/coco.yaml) 데이터와 `yolo val detect data=coco.yaml device=0` 명령으로 재현할 수 있습니다.

12
docs/ko/tasks/pose.md
View File

@ -35,12 +35,12 @@ keywords: Ultralytics, YOLO, YOLOv8, 포즈 추정, 키포인트 검출, 객체
| 모델 | 크기<br><sup>(픽셀) | mAP<sup>포즈<br>50-95 | mAP<sup>포즈<br>50 | 속도<br><sup>CPU ONNX<br>(ms) | 속도<br><sup>A100 TensorRT<br>(ms) | 파라미터<br><sup>(M) | FLOPs<br><sup>(B) | | 모델 | 크기<br><sup>(픽셀) | mAP<sup>포즈<br>50-95 | mAP<sup>포즈<br>50 | 속도<br><sup>CPU ONNX<br>(ms) | 속도<br><sup>A100 TensorRT<br>(ms) | 파라미터<br><sup>(M) | FLOPs<br><sup>(B) |
|------------------------------------------------------------------------------------------------------|-----------------|---------------------|------------------|-----------------------------|----------------------------------|------------------|-------------------| |------------------------------------------------------------------------------------------------------|-----------------|---------------------|------------------|-----------------------------|----------------------------------|------------------|-------------------|
| [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 | | [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 |
| [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 | | [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 |
| [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 | | [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 |
| [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 | | [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 |
| [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 | | [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 |
| [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 | | [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 |
- **mAP<sup>val</sup>** 값은 [COCO Keypoints val2017](http://cocodataset.org) 데이터셋에서 단일 모델 단일 규모를 기준으로 합니다. - **mAP<sup>val</sup>** 값은 [COCO Keypoints val2017](http://cocodataset.org) 데이터셋에서 단일 모델 단일 규모를 기준으로 합니다.
<br>재현하려면 `yolo val pose data=coco-pose.yaml device=0`을 사용하세요. <br>재현하려면 `yolo val pose data=coco-pose.yaml device=0`을 사용하세요.

10
docs/ko/tasks/segment.md
View File

@ -35,11 +35,11 @@ keywords: yolov8, 인스턴스 세그멘테이션, Ultralytics, COCO 데이터
| 모델 | 크기<br><sup>(픽셀) | mAP<sup>박스<br>50-95 | mAP<sup>마스크<br>50-95 | 속도<br><sup>CPU ONNX<br>(밀리초) | 속도<br><sup>A100 TensorRT<br>(밀리초) | 매개변수<br><sup>(M) | FLOPs<br><sup>(B) | | 모델 | 크기<br><sup>(픽셀) | mAP<sup>박스<br>50-95 | mAP<sup>마스크<br>50-95 | 속도<br><sup>CPU ONNX<br>(밀리초) | 속도<br><sup>A100 TensorRT<br>(밀리초) | 매개변수<br><sup>(M) | FLOPs<br><sup>(B) |
|----------------------------------------------------------------------------------------------|-----------------|---------------------|----------------------|------------------------------|-----------------------------------|------------------|-------------------| |----------------------------------------------------------------------------------------------|-----------------|---------------------|----------------------|------------------------------|-----------------------------------|------------------|-------------------|
| [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 | | [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 |
| [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 | | [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 |
| [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 | | [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 |
| [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 | | [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 |
| [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 | | [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 |
- **mAP<sup>val</sup>** 값들은 [COCO val2017](http://cocodataset.org) 데이터셋에서 단일 모델 단일 스케일로 얻은 값입니다. - **mAP<sup>val</sup>** 값들은 [COCO val2017](http://cocodataset.org) 데이터셋에서 단일 모델 단일 스케일로 얻은 값입니다.
<br>복제는 `yolo val segment data=coco.yaml device=0` 명령어로 실행할 수 있습니다. <br>복제는 `yolo val segment data=coco.yaml device=0` 명령어로 실행할 수 있습니다.

6
docs/pt/models/yolo-nas.md
View File

@ -92,9 +92,9 @@ Abaixo está uma visão geral detalhada de cada modelo, incluindo links para seu
| Tipo de Modelo | Pesos Pré-Treinados | Tarefas Suportadas | Inferência | Validação | Treinamento | Exportação | | Tipo de Modelo | Pesos Pré-Treinados | Tarefas Suportadas | Inferência | Validação | Treinamento | Exportação |
|----------------|-----------------------------------------------------------------------------------------------|-------------------------------------------|------------|-----------|-------------|------------| |----------------|-----------------------------------------------------------------------------------------------|-------------------------------------------|------------|-----------|-------------|------------|
| YOLO-NAS-s | [yolo_nas_s.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolo_nas_s.pt) | [Detecção de Objetos](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ | | YOLO-NAS-s | [yolo_nas_s.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolo_nas_s.pt) | [Detecção de Objetos](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ |
| YOLO-NAS-m | [yolo_nas_m.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolo_nas_m.pt) | [Detecção de Objetos](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ | | YOLO-NAS-m | [yolo_nas_m.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolo_nas_m.pt) | [Detecção de Objetos](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ |
| YOLO-NAS-l | [yolo_nas_l.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolo_nas_l.pt) | [Detecção de Objetos](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ | | YOLO-NAS-l | [yolo_nas_l.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolo_nas_l.pt) | [Detecção de Objetos](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ |
## Citações e Agradecimentos ## Citações e Agradecimentos

20
docs/pt/models/yolov5.md
View File

@ -40,17 +40,17 @@ Essa tabela oferece uma visão detalhada das variantes do modelo YOLOv5u, destac
| Modelo | YAML | tamanho<br><sup>(pixels) | mAP<sup>val<br>50-95 | Velocidade<br><sup>CPU ONNX<br>(ms) | Velocidade<br><sup>A100 TensorRT<br>(ms) | parâmetros<br><sup>(M) | FLOPs<br><sup>(B) | | Modelo | YAML | tamanho<br><sup>(pixels) | mAP<sup>val<br>50-95 | Velocidade<br><sup>CPU ONNX<br>(ms) | Velocidade<br><sup>A100 TensorRT<br>(ms) | parâmetros<br><sup>(M) | FLOPs<br><sup>(B) |
| --------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------| -------------------------| ----------------------| -------------------------------------| -------------------------------------- | ---------------------- | ----------------- | | --------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------| -------------------------| ----------------------| -------------------------------------| -------------------------------------- | ---------------------- | ----------------- |
| [yolov5nu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5nu.pt) | [yolov5n.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 34.3 | 73.6 | 1.06 | 2.6 | 7.7 | | [yolov5nu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5nu.pt) | [yolov5n.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 34.3 | 73.6 | 1.06 | 2.6 | 7.7 |
| [yolov5su.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5su.pt) | [yolov5s.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 43.0 | 120.7 | 1.27 | 9.1 | 24.0 | | [yolov5su.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5su.pt) | [yolov5s.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 43.0 | 120.7 | 1.27 | 9.1 | 24.0 |
| [yolov5mu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5mu.pt) | [yolov5m.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 49.0 | 233.9 | 1.86 | 25.1 | 64.2 | | [yolov5mu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5mu.pt) | [yolov5m.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 49.0 | 233.9 | 1.86 | 25.1 | 64.2 |
| [yolov5lu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5lu.pt) | [yolov5l.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 52.2 | 408.4 | 2.50 | 53.2 | 135.0 | | [yolov5lu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5lu.pt) | [yolov5l.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 52.2 | 408.4 | 2.50 | 53.2 | 135.0 |
| [yolov5xu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5xu.pt) | [yolov5x.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 53.2 | 763.2 | 3.81 | 97.2 | 246.4 | | [yolov5xu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5xu.pt) | [yolov5x.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 53.2 | 763.2 | 3.81 | 97.2 | 246.4 |
| | | | | | | | | | | | | | | | | |
| [yolov5n6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5n6u.pt) | [yolov5n6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 42.1 | 211.0 | 1.83 | 4.3 | 7.8 | | [yolov5n6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5n6u.pt) | [yolov5n6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 42.1 | 211.0 | 1.83 | 4.3 | 7.8 |
| [yolov5s6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5s6u.pt) | [yolov5s6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 48.6 | 422.6 | 2.34 | 15.3 | 24.6 | | [yolov5s6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5s6u.pt) | [yolov5s6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 48.6 | 422.6 | 2.34 | 15.3 | 24.6 |
| [yolov5m6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5m6u.pt) | [yolov5m6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 53.6 | 810.9 | 4.36 | 41.2 | 65.7 | | [yolov5m6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5m6u.pt) | [yolov5m6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 53.6 | 810.9 | 4.36 | 41.2 | 65.7 |
| [yolov5l6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5l6u.pt) | [yolov5l6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 55.7 | 1470.9 | 5.47 | 86.1 | 137.4 | | [yolov5l6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5l6u.pt) | [yolov5l6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 55.7 | 1470.9 | 5.47 | 86.1 | 137.4 |
| [yolov5x6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5x6u.pt) | [yolov5x6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 56.8 | 2436.5 | 8.98 | 155.4 | 250.7 | | [yolov5x6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5x6u.pt) | [yolov5x6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 56.8 | 2436.5 | 8.98 | 155.4 | 250.7 |
## Exemplos de Uso ## Exemplos de Uso

52
docs/pt/models/yolov8.md
View File

@ -44,11 +44,11 @@ Esta tabela fornece uma visão geral das variantes de modelos YOLOv8, destacando
| Modelo | tamanho<br><sup>(pixels) | mAP<sup>val<br>50-95 | Velocidade<br><sup>CPU ONNX<br>(ms) | Velocidade<br><sup>A100 TensorRT<br>(ms) | parâmetros<br><sup>(M) | FLOPs<br><sup>(B) | | Modelo | tamanho<br><sup>(pixels) | mAP<sup>val<br>50-95 | Velocidade<br><sup>CPU ONNX<br>(ms) | Velocidade<br><sup>A100 TensorRT<br>(ms) | parâmetros<br><sup>(M) | FLOPs<br><sup>(B) |
| --------------------------------------------------------------------------------------- | ----------------------- | -------------------- | ----------------------------------- | --------------------------------------- | ---------------------- | ------------------ | | --------------------------------------------------------------------------------------- | ----------------------- | -------------------- | ----------------------------------- | --------------------------------------- | ---------------------- | ------------------ |
| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt) | 640 | 37,3 | 80,4 | 0,99 | 3,2 | 8,7 | | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt) | 640 | 37,3 | 80,4 | 0,99 | 3,2 | 8,7 |
| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s.pt) | 640 | 44,9 | 128,4 | 1,20 | 11,2 | 28,6 | | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s.pt) | 640 | 44,9 | 128,4 | 1,20 | 11,2 | 28,6 |
| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m.pt) | 640 | 50,2 | 234,7 | 1,83 | 25,9 | 78,9 | | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m.pt) | 640 | 50,2 | 234,7 | 1,83 | 25,9 | 78,9 |
| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l.pt) | 640 | 52,9 | 375,2 | 2,39 | 43,7 | 165,2 | | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l.pt) | 640 | 52,9 | 375,2 | 2,39 | 43,7 | 165,2 |
| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x.pt) | 640 | 53,9 | 479,1 | 3,53 | 68,2 | 257,8 | | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x.pt) | 640 | 53,9 | 479,1 | 3,53 | 68,2 | 257,8 |
=== "Detecção (Open Images V7)" === "Detecção (Open Images V7)"
@ -56,11 +56,11 @@ Esta tabela fornece uma visão geral das variantes de modelos YOLOv8, destacando
| Modelo | tamanho<br><sup>(pixels) | mAP<sup>val<br>50-95 | Velocidade<br><sup>CPU ONNX<br>(ms) | Velocidade<br><sup>A100 TensorRT<br>(ms) | parâmetros<br><sup>(M) | FLOPs<br><sup>(B) | | Modelo | tamanho<br><sup>(pixels) | mAP<sup>val<br>50-95 | Velocidade<br><sup>CPU ONNX<br>(ms) | Velocidade<br><sup>A100 TensorRT<br>(ms) | parâmetros<br><sup>(M) | FLOPs<br><sup>(B) |
| ----------------------------------------------------------------------------------------- | ----------------------- | -------------------- | ----------------------------------- | --------------------------------------- | ---------------------- | ------------------ | | ----------------------------------------------------------------------------------------- | ----------------------- | -------------------- | ----------------------------------- | --------------------------------------- | ---------------------- | ------------------ |
| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-oiv7.pt) | 640 | 18,4 | 142,4 | 1,21 | 3,5 | 10,5 | | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-oiv7.pt) | 640 | 18,4 | 142,4 | 1,21 | 3,5 | 10,5 |
| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-oiv7.pt) | 640 | 27,7 | 183,1 | 1,40 | 11,4 | 29,7 | | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-oiv7.pt) | 640 | 27,7 | 183,1 | 1,40 | 11,4 | 29,7 |
| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-oiv7.pt) | 640 | 33,6 | 408,5 | 2,26 | 26,2 | 80,6 | | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-oiv7.pt) | 640 | 33,6 | 408,5 | 2,26 | 26,2 | 80,6 |
| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-oiv7.pt) | 640 | 34,9 | 596,9 | 2,43 | 44,1 | 167,4 | | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-oiv7.pt) | 640 | 34,9 | 596,9 | 2,43 | 44,1 | 167,4 |
| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-oiv7.pt) | 640 | 36,3 | 860,6 | 3,56 | 68,7 | 260,6 | | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-oiv7.pt) | 640 | 36,3 | 860,6 | 3,56 | 68,7 | 260,6 |
=== "Segmentação (COCO)" === "Segmentação (COCO)"
@ -68,11 +68,11 @@ Esta tabela fornece uma visão geral das variantes de modelos YOLOv8, destacando
| Modelo | tamanho<br><sup>(pixels) | mAP<sup>box<br>50-95 | mAP<sup>máscara<br>50-95 | Velocidade<br><sup>CPU ONNX<br>(ms) | Velocidade<br><sup>A100 TensorRT<br>(ms) | parâmetros<br><sup>(M) | FLOPs<br><sup>(B) | | Modelo | tamanho<br><sup>(pixels) | mAP<sup>box<br>50-95 | mAP<sup>máscara<br>50-95 | Velocidade<br><sup>CPU ONNX<br>(ms) | Velocidade<br><sup>A100 TensorRT<br>(ms) | parâmetros<br><sup>(M) | FLOPs<br><sup>(B) |
| ---------------------------------------------------------------------------------------------- | ----------------------- | -------------------- | ------------------------ | ----------------------------------- | --------------------------------------- | ---------------------- | ------------------ | | ---------------------------------------------------------------------------------------------- | ----------------------- | -------------------- | ------------------------ | ----------------------------------- | --------------------------------------- | ---------------------- | ------------------ |
| [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-seg.pt) | 640 | 36,7 | 30,5 | 96,1 | 1,21 | 3,4 | 12,6 | | [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-seg.pt) | 640 | 36,7 | 30,5 | 96,1 | 1,21 | 3,4 | 12,6 |
| [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-seg.pt) | 640 | 44,6 | 36,8 | 155,7 | 1,47 | 11,8 | 42,6 | | [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-seg.pt) | 640 | 44,6 | 36,8 | 155,7 | 1,47 | 11,8 | 42,6 |
| [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-seg.pt) | 640 | 49,9 | 40,8 | 317,0 | 2,18 | 27,3 | 110,2 | | [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-seg.pt) | 640 | 49,9 | 40,8 | 317,0 | 2,18 | 27,3 | 110,2 |
| [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-seg.pt) | 640 | 52,3 | 42,6 | 572,4 | 2,79 | 46,0 | 220,5 | | [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-seg.pt) | 640 | 52,3 | 42,6 | 572,4 | 2,79 | 46,0 | 220,5 |
| [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-seg.pt) | 640 | 53,4 | 43,4 | 712,1 | 4,02 | 71,8 | 344,1 | | [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-seg.pt) | 640 | 53,4 | 43,4 | 712,1 | 4,02 | 71,8 | 344,1 |
=== "Classificação (ImageNet)" === "Classificação (ImageNet)"
@ -80,11 +80,11 @@ Esta tabela fornece uma visão geral das variantes de modelos YOLOv8, destacando
| Modelo | tamanho<br><sup>(pixels) | acurácia<br><sup>top1 | acurácia<br><sup>top5 | Velocidade<br><sup>CPU ONNX<br>(ms) | Velocidade<br><sup>A100 TensorRT<br>(ms) | parâmetros<br><sup>(M) | FLOPs<br><sup>(B) a 640 | | Modelo | tamanho<br><sup>(pixels) | acurácia<br><sup>top1 | acurácia<br><sup>top5 | Velocidade<br><sup>CPU ONNX<br>(ms) | Velocidade<br><sup>A100 TensorRT<br>(ms) | parâmetros<br><sup>(M) | FLOPs<br><sup>(B) a 640 |
| ------------------------------------------------------------------------------------------------ | ----------------------- | --------------------- | --------------------- | ----------------------------------- | --------------------------------------- | ---------------------- | ------------------------ | | ------------------------------------------------------------------------------------------------ | ----------------------- | --------------------- | --------------------- | ----------------------------------- | --------------------------------------- | ---------------------- | ------------------------ |
| [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-cls.pt) | 224 | 66,6 | 87,0 | 12,9 | 0,31 | 2,7 | 4,3 | | [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-cls.pt) | 224 | 66,6 | 87,0 | 12,9 | 0,31 | 2,7 | 4,3 |
| [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-cls.pt) | 224 | 72,3 | 91,1 | 23,4 | 0,35 | 6,4 | 13,5 | | [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-cls.pt) | 224 | 72,3 | 91,1 | 23,4 | 0,35 | 6,4 | 13,5 |
| [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-cls.pt) | 224 | 76,4 | 93,2 | 85,4 | 0,62 | 17,0 | 42,7 | | [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-cls.pt) | 224 | 76,4 | 93,2 | 85,4 | 0,62 | 17,0 | 42,7 |
| [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-cls.pt) | 224 | 78,0 | 94,1 | 163,0 | 0,87 | 37,5 | 99,7 | | [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-cls.pt) | 224 | 78,0 | 94,1 | 163,0 | 0,87 | 37,5 | 99,7 |
| [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-cls.pt) | 224 | 78,4 | 94,3 | 232,0 | 1,01 | 57,4 | 154,8 | | [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-cls.pt) | 224 | 78,4 | 94,3 | 232,0 | 1,01 | 57,4 | 154,8 |
=== "Pose (COCO)" === "Pose (COCO)"
@ -92,12 +92,12 @@ Esta tabela fornece uma visão geral das variantes de modelos YOLOv8, destacando
| Modelo | tamanho<br><sup>(pixels) | mAP<sup>pose<br>50-95 | mAP<sup>pose<br>50 | Velocidade<br><sup>CPU ONNX<br>(ms) | Velocidade<br><sup>A100 TensorRT<br>(ms) | parâmetros<br><sup>(M) | FLOPs<br><sup>(B) | | Modelo | tamanho<br><sup>(pixels) | mAP<sup>pose<br>50-95 | mAP<sup>pose<br>50 | Velocidade<br><sup>CPU ONNX<br>(ms) | Velocidade<br><sup>A100 TensorRT<br>(ms) | parâmetros<br><sup>(M) | FLOPs<br><sup>(B) |
| ---------------------------------------------------------------------------------------------- | ----------------------- | --------------------- | ------------------ | ----------------------------------- | --------------------------------------- | ---------------------- | ------------------ | | ---------------------------------------------------------------------------------------------- | ----------------------- | --------------------- | ------------------ | ----------------------------------- | --------------------------------------- | ---------------------- | ------------------ |
| [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-pose.pt) | 640 | 50,4 | 80,1 | 131,8 | 1,18 | 3,3 | 9,2 | | [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-pose.pt) | 640 | 50,4 | 80,1 | 131,8 | 1,18 | 3,3 | 9,2 |
| [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-pose.pt) | 640 | 60,0 | 86,2 | 233,2 | 1,42 | 11,6 | 30,2 | | [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-pose.pt) | 640 | 60,0 | 86,2 | 233,2 | 1,42 | 11,6 | 30,2 |
| [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-pose.pt) | 640 | 65,0 | 88,8 | 456,3 | 2,00 | 26,4 | 81,0 | | [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-pose.pt) | 640 | 65,0 | 88,8 | 456,3 | 2,00 | 26,4 | 81,0 |
| [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-pose.pt) | 640 | 67,6 | 90,0 | 784,5 | 2,59 | 44,4 | 168,6 | | [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-pose.pt) | 640 | 67,6 | 90,0 | 784,5 | 2,59 | 44,4 | 168,6 |
| [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose.pt) | 640 | 69,2 | 90,2 | 1607,1 | 3,73 | 69,4 | 263,2 | | [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose.pt) | 640 | 69,2 | 90,2 | 1607,1 | 3,73 | 69,4 | 263,2 |
| [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose-p6.pt) | 1280 | 71,6 | 91,2 | 4088,7 | 10,04 | 99,1 | 1066,4 | | [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose-p6.pt) | 1280 | 71,6 | 91,2 | 4088,7 | 10,04 | 99,1 | 1066,4 |
## Exemplos de Uso ## Exemplos de Uso

10
docs/pt/tasks/classify.md
View File

@ -24,11 +24,11 @@ Aqui são mostrados os modelos pré-treinados YOLOv8 Classify. Modelos de Detec
| Modelo | Tamanho<br><sup>(pixels) | acurácia<br><sup>top1 | acurácia<br><sup>top5 | Velocidade<br><sup>CPU ONNX<br>(ms) | Velocidade<br><sup>A100 TensorRT<br>(ms) | parâmetros<br><sup>(M) | FLOPs<br><sup>(B) a 640 | | Modelo | Tamanho<br><sup>(pixels) | acurácia<br><sup>top1 | acurácia<br><sup>top5 | Velocidade<br><sup>CPU ONNX<br>(ms) | Velocidade<br><sup>A100 TensorRT<br>(ms) | parâmetros<br><sup>(M) | FLOPs<br><sup>(B) a 640 |
|----------------------------------------------------------------------------------------------|--------------------------|-----------------------|-----------------------|-------------------------------------|------------------------------------------|------------------------|-------------------------| |----------------------------------------------------------------------------------------------|--------------------------|-----------------------|-----------------------|-------------------------------------|------------------------------------------|------------------------|-------------------------|
| [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-cls.pt) | 224 | 66.6 | 87.0 | 12.9 | 0.31 | 2.7 | 4.3 | | [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-cls.pt) | 224 | 66.6 | 87.0 | 12.9 | 0.31 | 2.7 | 4.3 |
| [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-cls.pt) | 224 | 72.3 | 91.1 | 23.4 | 0.35 | 6.4 | 13.5 | | [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-cls.pt) | 224 | 72.3 | 91.1 | 23.4 | 0.35 | 6.4 | 13.5 |
| [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-cls.pt) | 224 | 76.4 | 93.2 | 85.4 | 0.62 | 17.0 | 42.7 | | [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-cls.pt) | 224 | 76.4 | 93.2 | 85.4 | 0.62 | 17.0 | 42.7 |
| [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-cls.pt) | 224 | 78.0 | 94.1 | 163.0 | 0.87 | 37.5 | 99.7 | | [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-cls.pt) | 224 | 78.0 | 94.1 | 163.0 | 0.87 | 37.5 | 99.7 |
| [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-cls.pt) | 224 | 78.4 | 94.3 | 232.0 | 1.01 | 57.4 | 154.8 | | [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-cls.pt) | 224 | 78.4 | 94.3 | 232.0 | 1.01 | 57.4 | 154.8 |
- Os valores de **acc** são as acurácias dos modelos no conjunto de validação do dataset [ImageNet](https://www.image-net.org/). - Os valores de **acc** são as acurácias dos modelos no conjunto de validação do dataset [ImageNet](https://www.image-net.org/).
<br>Reproduza com `yolo val classify data=path/to/ImageNet device=0` <br>Reproduza com `yolo val classify data=path/to/ImageNet device=0`

10
docs/pt/tasks/detect.md
View File

@ -35,11 +35,11 @@ Os [Modelos](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/cf
| Modelo | Tamanho<br><sup>(pixels) | mAP<sup>val<br>50-95 | Velocidade<br><sup>CPU ONNX<br>(ms) | Velocidade<br><sup>A100 TensorRT<br>(ms) | Parâmetros<br><sup>(M) | FLOPs<br><sup>(B) | | Modelo | Tamanho<br><sup>(pixels) | mAP<sup>val<br>50-95 | Velocidade<br><sup>CPU ONNX<br>(ms) | Velocidade<br><sup>A100 TensorRT<br>(ms) | Parâmetros<br><sup>(M) | FLOPs<br><sup>(B) |
|--------------------------------------------------------------------------------------|--------------------------|----------------------|-------------------------------------|------------------------------------------|------------------------|-------------------| |--------------------------------------------------------------------------------------|--------------------------|----------------------|-------------------------------------|------------------------------------------|------------------------|-------------------|
| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 | | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 |
| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 | | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 |
| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 | | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 |
| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 | | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 |
| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 | | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 |
- Os valores de **mAP<sup>val</sup>** são para um único modelo e uma única escala no dataset [COCO val2017](http://cocodataset.org). - Os valores de **mAP<sup>val</sup>** são para um único modelo e uma única escala no dataset [COCO val2017](http://cocodataset.org).
<br>Reproduza usando `yolo val detect data=coco.yaml device=0` <br>Reproduza usando `yolo val detect data=coco.yaml device=0`

12
docs/pt/tasks/pose.md
View File

@ -35,12 +35,12 @@ Os modelos YOLOv8 Pose pré-treinados são mostrados aqui. Os modelos Detect, Se
| Modelo | tamanho<br><sup>(pixels) | mAP<sup>pose<br>50-95 | mAP<sup>pose<br>50 | Velocidade<br><sup>CPU ONNX<br>(ms) | Velocidade<br><sup>A100 TensorRT<br>(ms) | parâmetros<br><sup>(M) | FLOPs<br><sup>(B) | | Modelo | tamanho<br><sup>(pixels) | mAP<sup>pose<br>50-95 | mAP<sup>pose<br>50 | Velocidade<br><sup>CPU ONNX<br>(ms) | Velocidade<br><sup>A100 TensorRT<br>(ms) | parâmetros<br><sup>(M) | FLOPs<br><sup>(B) |
|------------------------------------------------------------------------------------------------------|--------------------------|-----------------------|--------------------|-------------------------------------|------------------------------------------|------------------------|-------------------| |------------------------------------------------------------------------------------------------------|--------------------------|-----------------------|--------------------|-------------------------------------|------------------------------------------|------------------------|-------------------|
| [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 | | [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 |
| [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 | | [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 |
| [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 | | [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 |
| [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 | | [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 |
| [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 | | [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 |
| [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 | | [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 |
- **mAP<sup>val</sup>** valores são para um único modelo em escala única no conjunto de dados [COCO Keypoints val2017](http://cocodataset.org) - **mAP<sup>val</sup>** valores são para um único modelo em escala única no conjunto de dados [COCO Keypoints val2017](http://cocodataset.org)
. .

10
docs/pt/tasks/segment.md
View File

@ -35,11 +35,11 @@ Os modelos Segment pré-treinados do YOLOv8 estão mostrados aqui. Os modelos De
| Modelo | Tamanho<br><sup>(pixels) | mAP<sup>box<br>50-95 | mAP<sup>máscara<br>50-95 | Velocidade<br><sup>CPU ONNX<br>(ms) | Velocidade<br><sup>A100 TensorRT<br>(ms) | Parâmetros<br><sup>(M) | FLOPs<br><sup>(B) | | Modelo | Tamanho<br><sup>(pixels) | mAP<sup>box<br>50-95 | mAP<sup>máscara<br>50-95 | Velocidade<br><sup>CPU ONNX<br>(ms) | Velocidade<br><sup>A100 TensorRT<br>(ms) | Parâmetros<br><sup>(M) | FLOPs<br><sup>(B) |
|----------------------------------------------------------------------------------------------|--------------------------|----------------------|--------------------------|-------------------------------------|------------------------------------------|------------------------|-------------------| |----------------------------------------------------------------------------------------------|--------------------------|----------------------|--------------------------|-------------------------------------|------------------------------------------|------------------------|-------------------|
| [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 | | [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 |
| [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 | | [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 |
| [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 | | [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 |
| [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 | | [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 |
| [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 | | [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 |
- Os valores de **mAP<sup>val</sup>** são para um único modelo em uma única escala no conjunto de dados [COCO val2017](http://cocodataset.org). - Os valores de **mAP<sup>val</sup>** são para um único modelo em uma única escala no conjunto de dados [COCO val2017](http://cocodataset.org).
<br>Reproduza por meio de `yolo val segment data=coco.yaml device=0` <br>Reproduza por meio de `yolo val segment data=coco.yaml device=0`

6
docs/ru/models/yolo-nas.md
View File

@ -92,9 +92,9 @@ keywords: YOLO-NAS, Deci AI, обнаружение объектов, глубо
| Тип модели | Предварительно обученные веса | Поддерживаемые задачи | Вывод результатов | Проверка | Обучение | Экспорт | | Тип модели | Предварительно обученные веса | Поддерживаемые задачи | Вывод результатов | Проверка | Обучение | Экспорт |
|------------|-----------------------------------------------------------------------------------------------|--------------------------------------------|-------------------|----------|----------|---------| |------------|-----------------------------------------------------------------------------------------------|--------------------------------------------|-------------------|----------|----------|---------|
| YOLO-NAS-s | [yolo_nas_s.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolo_nas_s.pt) | [Обнаружение объектов](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ | | YOLO-NAS-s | [yolo_nas_s.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolo_nas_s.pt) | [Обнаружение объектов](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ |
| YOLO-NAS-m | [yolo_nas_m.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolo_nas_m.pt) | [Обнаружение объектов](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ | | YOLO-NAS-m | [yolo_nas_m.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolo_nas_m.pt) | [Обнаружение объектов](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ |
| YOLO-NAS-l | [yolo_nas_l.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolo_nas_l.pt) | [Обнаружение объектов](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ | | YOLO-NAS-l | [yolo_nas_l.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolo_nas_l.pt) | [Обнаружение объектов](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ |
## Цитирование и благодарности ## Цитирование и благодарности

20
docs/ru/models/yolov5.md
View File

@ -40,17 +40,17 @@ YOLOv5u представляет собой прогресс в методоло
| Модель | YAML | размер<br><sup>(пиксели) | mAP<sup>val<br>50-95 | Скорость<br><sup>CPU ONNX<br>(мс) | Скорость<br><sup>A100 TensorRT<br>(мс) | параметры<br><sup>(М) | FLOPs<br><sup>(Б) | | Модель | YAML | размер<br><sup>(пиксели) | mAP<sup>val<br>50-95 | Скорость<br><sup>CPU ONNX<br>(мс) | Скорость<br><sup>A100 TensorRT<br>(мс) | параметры<br><sup>(М) | FLOPs<br><sup>(Б) |
|-------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------|-------------------------|----------------------|--------------------------------|-------------------------------------|----------------------|-------------------| |-------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------|-------------------------|----------------------|--------------------------------|-------------------------------------|----------------------|-------------------|
| [yolov5nu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5nu.pt) | [yolov5n.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 34.3 | 73.6 | 1.06 | 2.6 | 7.7 | | [yolov5nu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5nu.pt) | [yolov5n.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 34.3 | 73.6 | 1.06 | 2.6 | 7.7 |
| [yolov5su.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5su.pt) | [yolov5s.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 43.0 | 120.7 | 1.27 | 9.1 | 24.0 | | [yolov5su.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5su.pt) | [yolov5s.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 43.0 | 120.7 | 1.27 | 9.1 | 24.0 |
| [yolov5mu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5mu.pt) | [yolov5m.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 49.0 | 233.9 | 1.86 | 25.1 | 64.2 | | [yolov5mu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5mu.pt) | [yolov5m.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 49.0 | 233.9 | 1.86 | 25.1 | 64.2 |
| [yolov5lu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5lu.pt) | [yolov5l.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 52.2 | 408.4 | 2.50 | 53.2 | 135.0 | | [yolov5lu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5lu.pt) | [yolov5l.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 52.2 | 408.4 | 2.50 | 53.2 | 135.0 |
| [yolov5xu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5xu.pt) | [yolov5x.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 53.2 | 763.2 | 3.81 | 97.2 | 246.4 | | [yolov5xu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5xu.pt) | [yolov5x.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 53.2 | 763.2 | 3.81 | 97.2 | 246.4 |
| | | | | | | | | | | | | | | | | |
| [yolov5n6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5n6u.pt) | [yolov5n6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 42.1 | 211.0 | 1.83 | 4.3 | 7.8 | | [yolov5n6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5n6u.pt) | [yolov5n6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 42.1 | 211.0 | 1.83 | 4.3 | 7.8 |
| [yolov5s6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5s6u.pt) | [yolov5s6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 48.6 | 422.6 | 2.34 | 15.3 | 24.6 | | [yolov5s6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5s6u.pt) | [yolov5s6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 48.6 | 422.6 | 2.34 | 15.3 | 24.6 |
| [yolov5m6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5m6u.pt) | [yolov5m6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 53.6 | 810.9 | 4.36 | 41.2 | 65.7 | | [yolov5m6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5m6u.pt) | [yolov5m6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 53.6 | 810.9 | 4.36 | 41.2 | 65.7 |
| [yolov5l6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5l6u.pt) | [yolov5l6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 55.7 | 1470.9 | 5.47 | 86.1 | 137.4 | | [yolov5l6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5l6u.pt) | [yolov5l6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 55.7 | 1470.9 | 5.47 | 86.1 | 137.4 |
| [yolov5x6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5x6u.pt) | [yolov5x6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 56.8 | 2436.5 | 8.98 | 155.4 | 250.7 | | [yolov5x6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5x6u.pt) | [yolov5x6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 56.8 | 2436.5 | 8.98 | 155.4 | 250.7 |
## Примеры использования ## Примеры использования

52
docs/ru/models/yolov8.md
View File

@ -44,11 +44,11 @@ YOLOv8 - это последняя версия в серии детекторо
| Модель | размер<br><sup>(пиксели) | mAP<sup>val<br>50-95 | Скорость<br><sup>CPU ONNX<br>(мс) | Скорость<br><sup>A100 TensorRT<br>(мс) | параметры<br><sup>(М) | FLOPs<br><sup>(Б) | | Модель | размер<br><sup>(пиксели) | mAP<sup>val<br>50-95 | Скорость<br><sup>CPU ONNX<br>(мс) | Скорость<br><sup>A100 TensorRT<br>(мс) | параметры<br><sup>(М) | FLOPs<br><sup>(Б) |
| ------------------------------------------------------------------------------------ | --------------------- | -------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- | | ------------------------------------------------------------------------------------ | --------------------- | -------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 | | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 |
| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 | | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 |
| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 | | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 |
| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 | | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 |
| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 | | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 |
=== "Обнаружение (Open Images V7)" === "Обнаружение (Open Images V7)"
@ -56,11 +56,11 @@ YOLOv8 - это последняя версия в серии детекторо
| Модель | размер<br><sup>(пиксели) | mAP<sup>val<br>50-95 | Скорость<br><sup>CPU ONNX<br>(мс) | Скорость<br><sup>A100 TensorRT<br>(мс) | параметры<br><sup>(М) | FLOPs<br><sup>(Б) | | Модель | размер<br><sup>(пиксели) | mAP<sup>val<br>50-95 | Скорость<br><sup>CPU ONNX<br>(мс) | Скорость<br><sup>A100 TensorRT<br>(мс) | параметры<br><sup>(М) | FLOPs<br><sup>(Б) |
| ----------------------------------------------------------------------------------------- | --------------------- | -------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- | | ----------------------------------------------------------------------------------------- | --------------------- | -------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-oiv7.pt) | 640 | 18.4 | 142.4 | 1.21 | 3.5 | 10.5 | | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-oiv7.pt) | 640 | 18.4 | 142.4 | 1.21 | 3.5 | 10.5 |
| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-oiv7.pt) | 640 | 27.7 | 183.1 | 1.40 | 11.4 | 29.7 | | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-oiv7.pt) | 640 | 27.7 | 183.1 | 1.40 | 11.4 | 29.7 |
| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-oiv7.pt) | 640 | 33.6 | 408.5 | 2.26 | 26.2 | 80.6 | | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-oiv7.pt) | 640 | 33.6 | 408.5 | 2.26 | 26.2 | 80.6 |
| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-oiv7.pt) | 640 | 34.9 | 596.9 | 2.43 | 44.1 | 167.4 | | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-oiv7.pt) | 640 | 34.9 | 596.9 | 2.43 | 44.1 | 167.4 |
| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-oiv7.pt) | 640 | 36.3 | 860.6 | 3.56 | 68.7 | 260.6 | | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-oiv7.pt) | 640 | 36.3 | 860.6 | 3.56 | 68.7 | 260.6 |
=== "Сегментация (COCO)" === "Сегментация (COCO)"
@ -68,11 +68,11 @@ YOLOv8 - это последняя версия в серии детекторо
| Модель | размер<br><sup>(пиксели) | mAP<sup>box<br>50-95 | mAP<sup>mask<br>50-95 | Скорость<br><sup>CPU ONNX<br>(мс) | Скорость<br><sup>A100 TensorRT<br>(мс) | параметры<br><sup>(M) | FLOPs<br><sup>(Б) | | Модель | размер<br><sup>(пиксели) | mAP<sup>box<br>50-95 | mAP<sup>mask<br>50-95 | Скорость<br><sup>CPU ONNX<br>(мс) | Скорость<br><sup>A100 TensorRT<br>(мс) | параметры<br><sup>(M) | FLOPs<br><sup>(Б) |
| -------------------------------------------------------------------------------------------- | --------------------- | -------------------- | --------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- | | -------------------------------------------------------------------------------------------- | --------------------- | -------------------- | --------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
| [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 | | [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 |
| [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 | | [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 |
| [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 | | [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 |
| [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 | | [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 |
| [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 | | [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 |
=== "Классификация (ImageNet)" === "Классификация (ImageNet)"
@ -80,11 +80,11 @@ YOLOv8 - это последняя версия в серии детекторо
| Модель | размер<br><sup>(пиксели) | acc<br><sup>top1 | acc<br><sup>top5 | Скорость<br><sup>CPU ONNX<br>(мс) | Скорость<br><sup>A100 TensorRT<br>(мс) | параметры<br><sup>(M) | FLOPs<br><sup>(Б) при 640 | | Модель | размер<br><sup>(пиксели) | acc<br><sup>top1 | acc<br><sup>top5 | Скорость<br><sup>CPU ONNX<br>(мс) | Скорость<br><sup>A100 TensorRT<br>(мс) | параметры<br><sup>(M) | FLOPs<br><sup>(Б) при 640 |
| -------------------------------------------------------------------------------------------- | --------------------- | ---------------- | ---------------- | ------------------------------ | ----------------------------------- | ------------------ | ------------------------ | | -------------------------------------------------------------------------------------------- | --------------------- | ---------------- | ---------------- | ------------------------------ | ----------------------------------- | ------------------ | ------------------------ |
| [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-cls.pt) | 224 | 66.6 | 87.0 | 12.9 | 0.31 | 2.7 | 4.3 | | [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-cls.pt) | 224 | 66.6 | 87.0 | 12.9 | 0.31 | 2.7 | 4.3 |
| [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-cls.pt) | 224 | 72.3 | 91.1 | 23.4 | 0.35 | 6.4 | 13.5 | | [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-cls.pt) | 224 | 72.3 | 91.1 | 23.4 | 0.35 | 6.4 | 13.5 |
| [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-cls.pt) | 224 | 76.4 | 93.2 | 85.4 | 0.62 | 17.0 | 42.7 | | [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-cls.pt) | 224 | 76.4 | 93.2 | 85.4 | 0.62 | 17.0 | 42.7 |
| [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-cls.pt) | 224 | 78.0 | 94.1 | 163.0 | 0.87 | 37.5 | 99.7 | | [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-cls.pt) | 224 | 78.0 | 94.1 | 163.0 | 0.87 | 37.5 | 99.7 |
| [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-cls.pt) | 224 | 78.4 | 94.3 | 232.0 | 1.01 | 57.4 | 154.8 | | [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-cls.pt) | 224 | 78.4 | 94.3 | 232.0 | 1.01 | 57.4 | 154.8 |
=== "Поза (COCO)" === "Поза (COCO)"
@ -92,12 +92,12 @@ YOLOv8 - это последняя версия в серии детекторо
| Модель | размер<br><sup>(пиксели) | mAP<sup>pose<br>50-95 | mAP<sup>pose<br>50 | Скорость<br><sup>CPU ONNX<br>(мс) | Скорость<br><sup>A100 TensorRT<br>(мс) | параметры<br><sup>(M) | FLOPs<br><sup>(Б) | | Модель | размер<br><sup>(пиксели) | mAP<sup>pose<br>50-95 | mAP<sup>pose<br>50 | Скорость<br><sup>CPU ONNX<br>(мс) | Скорость<br><sup>A100 TensorRT<br>(мс) | параметры<br><sup>(M) | FLOPs<br><sup>(Б) |
| ---------------------------------------------------------------------------------------------------- | --------------------- | --------------------- | ------------------ | ------------------------------ | ----------------------------------- | ------------------ | ----------------- | | ---------------------------------------------------------------------------------------------------- | --------------------- | --------------------- | ------------------ | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
| [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 | | [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 |
| [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 | | [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 |
| [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 | | [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 |
| [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 | | [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 |
| [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 | | [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 |
| [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 | | [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 |
## Примеры использования ## Примеры использования

10
docs/ru/tasks/classify.md
View File

@ -24,11 +24,11 @@ keywords: Ultralytics, YOLOv8, классификация изображений
| Модель | Размер<br><sup>(пиксели) | Точность<br><sup>top1 | Точность<br><sup>top5 | Скорость<br><sup>CPU ONNX<br>(мс) | Скорость<br><sup>A100 TensorRT<br>(мс) | Параметры<br><sup>(М) | FLOPs<br><sup>(Б) на 640 | | Модель | Размер<br><sup>(пиксели) | Точность<br><sup>top1 | Точность<br><sup>top5 | Скорость<br><sup>CPU ONNX<br>(мс) | Скорость<br><sup>A100 TensorRT<br>(мс) | Параметры<br><sup>(М) | FLOPs<br><sup>(Б) на 640 |
|----------------------------------------------------------------------------------------------|--------------------------|-----------------------|-----------------------|-----------------------------------|----------------------------------------|-----------------------|--------------------------| |----------------------------------------------------------------------------------------------|--------------------------|-----------------------|-----------------------|-----------------------------------|----------------------------------------|-----------------------|--------------------------|
| [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-cls.pt) | 224 | 66.6 | 87.0 | 12.9 | 0.31 | 2.7 | 4.3 | | [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-cls.pt) | 224 | 66.6 | 87.0 | 12.9 | 0.31 | 2.7 | 4.3 |
| [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-cls.pt) | 224 | 72.3 | 91.1 | 23.4 | 0.35 | 6.4 | 13.5 | | [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-cls.pt) | 224 | 72.3 | 91.1 | 23.4 | 0.35 | 6.4 | 13.5 |
| [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-cls.pt) | 224 | 76.4 | 93.2 | 85.4 | 0.62 | 17.0 | 42.7 | | [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-cls.pt) | 224 | 76.4 | 93.2 | 85.4 | 0.62 | 17.0 | 42.7 |
| [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-cls.pt) | 224 | 78.0 | 94.1 | 163.0 | 0.87 | 37.5 | 99.7 | | [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-cls.pt) | 224 | 78.0 | 94.1 | 163.0 | 0.87 | 37.5 | 99.7 |
| [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-cls.pt) | 224 | 78.4 | 94.3 | 232.0 | 1.01 | 57.4 | 154.8 | | [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-cls.pt) | 224 | 78.4 | 94.3 | 232.0 | 1.01 | 57.4 | 154.8 |
- Значения **точность** указывают на точность модели на валидационном наборе данных [ImageNet](https://www.image-net.org/). - Значения **точность** указывают на точность модели на валидационном наборе данных [ImageNet](https://www.image-net.org/).
<br>Повторить результаты можно с помощью `yolo val classify data=path/to/ImageNet device=0`. <br>Повторить результаты можно с помощью `yolo val classify data=path/to/ImageNet device=0`.

10
docs/ru/tasks/detect.md
View File

@ -35,11 +35,11 @@ keywords: YOLOv8, Ultralytics, обнаружение объектов, пред
| Модель | размер<br><sup>(пиксели) | mAP<sup>val<br>50-95 | Скорость<br><sup>CPU ONNX<br>(мс) | Скорость<br><sup>A100 TensorRT<br>(мс) | параметры<br><sup>(М) | FLOPs<br><sup>(Б) | | Модель | размер<br><sup>(пиксели) | mAP<sup>val<br>50-95 | Скорость<br><sup>CPU ONNX<br>(мс) | Скорость<br><sup>A100 TensorRT<br>(мс) | параметры<br><sup>(М) | FLOPs<br><sup>(Б) |
|--------------------------------------------------------------------------------------|--------------------------|----------------------|-----------------------------------|----------------------------------------|-----------------------|-------------------| |--------------------------------------------------------------------------------------|--------------------------|----------------------|-----------------------------------|----------------------------------------|-----------------------|-------------------|
| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 | | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 |
| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 | | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 |
| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 | | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 |
| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 | | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 |
| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 | | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 |
- **mAP<sup>val</sup>** значения для одиночной модели одиночного масштаба на датасете [COCO val2017](http://cocodataset.org). - **mAP<sup>val</sup>** значения для одиночной модели одиночного масштаба на датасете [COCO val2017](http://cocodataset.org).
<br>Для воспроизведения используйте `yolo val detect data=coco.yaml device=0` <br>Для воспроизведения используйте `yolo val detect data=coco.yaml device=0`

12
docs/ru/tasks/pose.md
View File

@ -25,12 +25,12 @@ description: Узнайте, как использовать Ultralytics YOLOv8
| Модель | размер<br><sup>(пиксели) | mAP<sup>pose<br>50-95 | mAP<sup>pose<br>50 | Скорость<br><sup>CPU ONNX<br>(мс) | Скорость<br><sup>A100 TensorRT<br>(мс) | параметры<br><sup>(М) | FLOPs<br><sup>(Б) | | Модель | размер<br><sup>(пиксели) | mAP<sup>pose<br>50-95 | mAP<sup>pose<br>50 | Скорость<br><sup>CPU ONNX<br>(мс) | Скорость<br><sup>A100 TensorRT<br>(мс) | параметры<br><sup>(М) | FLOPs<br><sup>(Б) |
|------------------------------------------------------------------------------------------------------|--------------------------|-----------------------|--------------------|-----------------------------------|----------------------------------------|-----------------------|-------------------| |------------------------------------------------------------------------------------------------------|--------------------------|-----------------------|--------------------|-----------------------------------|----------------------------------------|-----------------------|-------------------|
| [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 | | [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 |
| [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 | | [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 |
| [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 | | [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 |
| [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 | | [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 |
| [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 | | [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 |
| [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 | | [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 |
- **mAP<sup>val</sup>** значения для одной модели одиночного масштаба на наборе данных [COCO Keypoints val2017](http://cocodataset.org). - **mAP<sup>val</sup>** значения для одной модели одиночного масштаба на наборе данных [COCO Keypoints val2017](http://cocodataset.org).
<br>Воспроизводится с помощью: `yolo val pose data=coco-pose.yaml device=0` <br>Воспроизводится с помощью: `yolo val pose data=coco-pose.yaml device=0`

10
docs/ru/tasks/segment.md
View File

@ -35,11 +35,11 @@ keywords: yolov8, сегментация объектов, Ultralytics, набо
| Модель | размер<br><sup>(пиксели) | mAP<sup>box<br>50-95 | mAP<sup>mask<br>50-95 | Скорость<br><sup>CPU ONNX<br>(мс) | Скорость<br><sup>A100 TensorRT<br>(мс) | параметры<br><sup>(М) | FLOPs<br><sup>(B) | | Модель | размер<br><sup>(пиксели) | mAP<sup>box<br>50-95 | mAP<sup>mask<br>50-95 | Скорость<br><sup>CPU ONNX<br>(мс) | Скорость<br><sup>A100 TensorRT<br>(мс) | параметры<br><sup>(М) | FLOPs<br><sup>(B) |
|----------------------------------------------------------------------------------------------|--------------------------|----------------------|-----------------------|-----------------------------------|----------------------------------------|-----------------------|-------------------| |----------------------------------------------------------------------------------------------|--------------------------|----------------------|-----------------------|-----------------------------------|----------------------------------------|-----------------------|-------------------|
| [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 | | [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 |
| [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 | | [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 |
| [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 | | [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 |
| [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 | | [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 |
| [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 | | [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 |
- Значения **mAP<sup>val</sup>** для одиночной модели одиночного масштаба на наборе данных [COCO val2017](http://cocodataset.org). - Значения **mAP<sup>val</sup>** для одиночной модели одиночного масштаба на наборе данных [COCO val2017](http://cocodataset.org).
<br>Воспроизведите с помощью `yolo val segment data=coco.yaml device=0` <br>Воспроизведите с помощью `yolo val segment data=coco.yaml device=0`

6
docs/zh/models/yolo-nas.md
View File

@ -92,9 +92,9 @@ keywords: YOLO-NAS, Deci AI, 物体检测, 深度学习, 神经架构搜索, Ult
| 模型类型 | 预训练权重链接 | 支持的任务 | 推理 | 验证 | 训练 | 导出 | | 模型类型 | 预训练权重链接 | 支持的任务 | 推理 | 验证 | 训练 | 导出 |
|------------|-----------------------------------------------------------------------------------------------|----------------------------|----|----|----|----| |------------|-----------------------------------------------------------------------------------------------|----------------------------|----|----|----|----|
| YOLO-NAS-s | [yolo_nas_s.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolo_nas_s.pt) | [物体检测](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ | | YOLO-NAS-s | [yolo_nas_s.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolo_nas_s.pt) | [物体检测](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ |
| YOLO-NAS-m | [yolo_nas_m.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolo_nas_m.pt) | [物体检测](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ | | YOLO-NAS-m | [yolo_nas_m.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolo_nas_m.pt) | [物体检测](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ |
| YOLO-NAS-l | [yolo_nas_l.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolo_nas_l.pt) | [物体检测](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ | | YOLO-NAS-l | [yolo_nas_l.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolo_nas_l.pt) | [物体检测](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ |
## 引用和致谢 ## 引用和致谢

20
docs/zh/models/yolov5.md
View File

@ -40,17 +40,17 @@ YOLOv5u是目标检测方法的一种进步。YOLOv5u源于Ultralytics开发的[
| 模型 | YAML | 大小<br><sup>（像素） | mAP<sup>val<br>50-95 | 速度<br><sup>CPU ONNX<br>（毫秒） | 速度<br><sup>A100 TensorRT<br>（毫秒） | 参数数<br><sup>（百万） | FLOPs<br><sup>（十亿） | | 模型 | YAML | 大小<br><sup>（像素） | mAP<sup>val<br>50-95 | 速度<br><sup>CPU ONNX<br>（毫秒） | 速度<br><sup>A100 TensorRT<br>（毫秒） | 参数数<br><sup>（百万） | FLOPs<br><sup>（十亿） |
|---------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------|-----------------------|----------------------|--------------------------------|-------------------------------------|--------------------|-------------------| |---------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------|-----------------------|----------------------|--------------------------------|-------------------------------------|--------------------|-------------------|
| [yolov5nu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5nu.pt) | [yolov5n.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 34.3 | 73.6 | 1.06 | 2.6 | 7.7 | | [yolov5nu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5nu.pt) | [yolov5n.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 34.3 | 73.6 | 1.06 | 2.6 | 7.7 |
| [yolov5su.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5su.pt) | [yolov5s.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 43.0 | 120.7 | 1.27 | 9.1 | 24.0 | | [yolov5su.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5su.pt) | [yolov5s.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 43.0 | 120.7 | 1.27 | 9.1 | 24.0 |
| [yolov5mu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5mu.pt) | [yolov5m.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 49.0 | 233.9 | 1.86 | 25.1 | 64.2 | | [yolov5mu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5mu.pt) | [yolov5m.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 49.0 | 233.9 | 1.86 | 25.1 | 64.2 |
| [yolov5lu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5lu.pt) | [yolov5l.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 52.2 | 408.4 | 2.50 | 53.2 | 135.0 | | [yolov5lu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5lu.pt) | [yolov5l.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 52.2 | 408.4 | 2.50 | 53.2 | 135.0 |
| [yolov5xu.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5xu.pt) | [yolov5x.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 53.2 | 763.2 | 3.81 | 97.2 | 246.4 | | [yolov5xu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5xu.pt) | [yolov5x.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 53.2 | 763.2 | 3.81 | 97.2 | 246.4 |
| | | | | | | | | | | | | | | | | |
| [yolov5n6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5n6u.pt) | [yolov5n6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 42.1 | 211.0 | 1.83 | 4.3 | 7.8 | | [yolov5n6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5n6u.pt) | [yolov5n6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 42.1 | 211.0 | 1.83 | 4.3 | 7.8 |
| [yolov5s6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5s6u.pt) | [yolov5s6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 48.6 | 422.6 | 2.34 | 15.3 | 24.6 | | [yolov5s6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5s6u.pt) | [yolov5s6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 48.6 | 422.6 | 2.34 | 15.3 | 24.6 |
| [yolov5m6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5m6u.pt) | [yolov5m6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 53.6 | 810.9 | 4.36 | 41.2 | 65.7 | | [yolov5m6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5m6u.pt) | [yolov5m6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 53.6 | 810.9 | 4.36 | 41.2 | 65.7 |
| [yolov5l6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5l6u.pt) | [yolov5l6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 55.7 | 1470.9 | 5.47 | 86.1 | 137.4 | | [yolov5l6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5l6u.pt) | [yolov5l6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 55.7 | 1470.9 | 5.47 | 86.1 | 137.4 |
| [yolov5x6u.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5x6u.pt) | [yolov5x6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 56.8 | 2436.5 | 8.98 | 155.4 | 250.7 | | [yolov5x6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5x6u.pt) | [yolov5x6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 56.8 | 2436.5 | 8.98 | 155.4 | 250.7 |
## 使用示例 ## 使用示例

52
docs/zh/models/yolov8.md
View File

@ -44,11 +44,11 @@ YOLOv8系列的每个变体都针对其相应的任务进行了优化，确保
| 模型 | 大小<br><sup>(pixels) | mAP<sup>val<br>50-95 | 速度<br><sup>CPU ONNX<br>(ms) | 速度<br><sup>A100 TensorRT<br>(ms) | 参数<br><sup>(M) | FLOPs<br><sup>(B) | | 模型 | 大小<br><sup>(pixels) | mAP<sup>val<br>50-95 | 速度<br><sup>CPU ONNX<br>(ms) | 速度<br><sup>A100 TensorRT<br>(ms) | 参数<br><sup>(M) | FLOPs<br><sup>(B) |
| ---------------------------------------------------------------------------------------- | --------------------- | -------------------- | --------------------------------- | ---------------------------------- | ------------------ | ----------------- | | ---------------------------------------------------------------------------------------- | --------------------- | -------------------- | --------------------------------- | ---------------------------------- | ------------------ | ----------------- |
| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 | | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 |
| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 | | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 |
| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 | | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 |
| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 | | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 |
| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 | | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 |
=== "检测（Open Images V7）" === "检测（Open Images V7）"
@ -56,11 +56,11 @@ YOLOv8系列的每个变体都针对其相应的任务进行了优化，确保
| 模型 | 大小<br><sup>(pixels) | mAP<sup>val<br>50-95 | 速度<br><sup>CPU ONNX<br>(ms) | 速度<br><sup>A100 TensorRT<br>(ms) | 参数<br><sup>(M) | FLOPs<br><sup>(B) | | 模型 | 大小<br><sup>(pixels) | mAP<sup>val<br>50-95 | 速度<br><sup>CPU ONNX<br>(ms) | 速度<br><sup>A100 TensorRT<br>(ms) | 参数<br><sup>(M) | FLOPs<br><sup>(B) |
| ------------------------------------------------------------------------------------------- | --------------------- | -------------------- | ------------------------------ | ---------------------------------- | ------------------ | ----------------- | | ------------------------------------------------------------------------------------------- | --------------------- | -------------------- | ------------------------------ | ---------------------------------- | ------------------ | ----------------- |
| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-oiv7.pt) | 640 | 18.4 | 142.4 | 1.21 | 3.5 | 10.5 | | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-oiv7.pt) | 640 | 18.4 | 142.4 | 1.21 | 3.5 | 10.5 |
| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-oiv7.pt) | 640 | 27.7 | 183.1 | 1.40 | 11.4 | 29.7 | | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-oiv7.pt) | 640 | 27.7 | 183.1 | 1.40 | 11.4 | 29.7 |
| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-oiv7.pt) | 640 | 33.6 | 408.5 | 2.26 | 26.2 | 80.6 | | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-oiv7.pt) | 640 | 33.6 | 408.5 | 2.26 | 26.2 | 80.6 |
| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-oiv7.pt) | 640 | 34.9 | 596.9 | 2.43 | 44.1 | 167.4 | | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-oiv7.pt) | 640 | 34.9 | 596.9 | 2.43 | 44.1 | 167.4 |
| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-oiv7.pt) | 640 | 36.3 | 860.6 | 3.56 | 68.7 | 260.6 | | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-oiv7.pt) | 640 | 36.3 | 860.6 | 3.56 | 68.7 | 260.6 |
=== "分割（COCO）" === "分割（COCO）"
@ -68,11 +68,11 @@ YOLOv8系列的每个变体都针对其相应的任务进行了优化，确保
| 模型 | 大小<br><sup>(pixels) | mAP<sup>box<br>50-95 | mAP<sup>mask<br>50-95 | 速度<br><sup>CPU ONNX<br>(ms) | 速度<br><sup>A100 TensorRT<br>(ms) | 参数<br><sup>(M) | FLOPs<br><sup>(B) | | 模型 | 大小<br><sup>(pixels) | mAP<sup>box<br>50-95 | mAP<sup>mask<br>50-95 | 速度<br><sup>CPU ONNX<br>(ms) | 速度<br><sup>A100 TensorRT<br>(ms) | 参数<br><sup>(M) | FLOPs<br><sup>(B) |
| -------------------------------------------------------------------------------------------- | --------------------- | -------------------- | --------------------- | ------------------------------ | ---------------------------------- | ------------------ | ----------------- | | -------------------------------------------------------------------------------------------- | --------------------- | -------------------- | --------------------- | ------------------------------ | ---------------------------------- | ------------------ | ----------------- |
| [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 | | [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 |
| [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 | | [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 |
| [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 | | [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 |
| [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 | | [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 |
| [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 | | [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 |
=== "分类（ImageNet）" === "分类（ImageNet）"
@ -80,11 +80,11 @@ YOLOv8系列的每个变体都针对其相应的任务进行了优化，确保
| 模型 | 大小<br><sup>(pixels) | 准确率<br><sup>top1 | 准确率<br><sup>top5 | 速度<br><sup>CPU ONNX<br>(ms) | 速度<br><sup>A100 TensorRT<br>(ms) | 参数<br><sup>(M) | FLOPs<br><sup>(B) at 640 | | 模型 | 大小<br><sup>(pixels) | 准确率<br><sup>top1 | 准确率<br><sup>top5 | 速度<br><sup>CPU ONNX<br>(ms) | 速度<br><sup>A100 TensorRT<br>(ms) | 参数<br><sup>(M) | FLOPs<br><sup>(B) at 640 |
| ---------------------------------------------------------------------------------------------- | --------------------- | ------------------ | ------------------ | ------------------------------ | ---------------------------------- | ------------------ | ------------------------ | | ---------------------------------------------------------------------------------------------- | --------------------- | ------------------ | ------------------ | ------------------------------ | ---------------------------------- | ------------------ | ------------------------ |
| [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-cls.pt) | 224 | 66.6 | 87.0 | 12.9 | 0.31 | 2.7 | 4.3 | | [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-cls.pt) | 224 | 66.6 | 87.0 | 12.9 | 0.31 | 2.7 | 4.3 |
| [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-cls.pt) | 224 | 72.3 | 91.1 | 23.4 | 0.35 | 6.4 | 13.5 | | [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-cls.pt) | 224 | 72.3 | 91.1 | 23.4 | 0.35 | 6.4 | 13.5 |
| [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-cls.pt) | 224 | 76.4 | 93.2 | 85.4 | 0.62 | 17.0 | 42.7 | | [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-cls.pt) | 224 | 76.4 | 93.2 | 85.4 | 0.62 | 17.0 | 42.7 |
| [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-cls.pt) | 224 | 78.0 | 94.1 | 163.0 | 0.87 | 37.5 | 99.7 | | [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-cls.pt) | 224 | 78.0 | 94.1 | 163.0 | 0.87 | 37.5 | 99.7 |
| [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-cls.pt) | 224 | 78.4 | 94.3 | 232.0 | 1.01 | 57.4 | 154.8 | | [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-cls.pt) | 224 | 78.4 | 94.3 | 232.0 | 1.01 | 57.4 | 154.8 |
=== "姿态（COCO）" === "姿态（COCO）"
@ -92,12 +92,12 @@ YOLOv8系列的每个变体都针对其相应的任务进行了优化，确保
| 模型 | 大小<br><sup>(pixels) | mAP<sup>pose<br>50-95 | mAP<sup>pose<br>50 | 速度<br><sup>CPU ONNX<br>(ms) | 速度<br><sup>A100 TensorRT<br>(ms) | 参数<br><sup>(M) | FLOPs<br><sup>(B) | | 模型 | 大小<br><sup>(pixels) | mAP<sup>pose<br>50-95 | mAP<sup>pose<br>50 | 速度<br><sup>CPU ONNX<br>(ms) | 速度<br><sup>A100 TensorRT<br>(ms) | 参数<br><sup>(M) | FLOPs<br><sup>(B) |
| ---------------------------------------------------------------------------------------------------- | --------------------- | --------------------- | ------------------ | ------------------------------ | ---------------------------------- | ------------------ | ----------------- | | ---------------------------------------------------------------------------------------------------- | --------------------- | --------------------- | ------------------ | ------------------------------ | ---------------------------------- | ------------------ | ----------------- |
| [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 | | [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 |
| [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 | | [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 |
| [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 | | [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 |
| [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 | | [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 |
| [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 | | [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 |
| [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 | | [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 |
## 用法示例 ## 用法示例

10
docs/zh/tasks/classify.md
View File

@ -24,11 +24,11 @@ keywords: Ultralytics, YOLOv8, 图像分类, 预训练模型, YOLOv8n-cls, 训
| 模型 | 尺寸<br><sup>(像素) | 准确率<br><sup>top1 | 准确率<br><sup>top5 | 速度<br><sup>CPU ONNX<br>(ms) | 速度<br><sup>A100 TensorRT<br>(ms) | 参数<br><sup>(M) | FLOPs<br><sup>(B) at 640 | | 模型 | 尺寸<br><sup>(像素) | 准确率<br><sup>top1 | 准确率<br><sup>top5 | 速度<br><sup>CPU ONNX<br>(ms) | 速度<br><sup>A100 TensorRT<br>(ms) | 参数<br><sup>(M) | FLOPs<br><sup>(B) at 640 |
|----------------------------------------------------------------------------------------------|-----------------|------------------|------------------|-----------------------------|----------------------------------|----------------|--------------------------| |----------------------------------------------------------------------------------------------|-----------------|------------------|------------------|-----------------------------|----------------------------------|----------------|--------------------------|
| [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-cls.pt) | 224 | 66.6 | 87.0 | 12.9 | 0.31 | 2.7 | 4.3 | | [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-cls.pt) | 224 | 66.6 | 87.0 | 12.9 | 0.31 | 2.7 | 4.3 |
| [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-cls.pt) | 224 | 72.3 | 91.1 | 23.4 | 0.35 | 6.4 | 13.5 | | [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-cls.pt) | 224 | 72.3 | 91.1 | 23.4 | 0.35 | 6.4 | 13.5 |
| [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-cls.pt) | 224 | 76.4 | 93.2 | 85.4 | 0.62 | 17.0 | 42.7 | | [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-cls.pt) | 224 | 76.4 | 93.2 | 85.4 | 0.62 | 17.0 | 42.7 |
| [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-cls.pt) | 224 | 78.0 | 94.1 | 163.0 | 0.87 | 37.5 | 99.7 | | [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-cls.pt) | 224 | 78.0 | 94.1 | 163.0 | 0.87 | 37.5 | 99.7 |
| [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-cls.pt) | 224 | 78.4 | 94.3 | 232.0 | 1.01 | 57.4 | 154.8 | | [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-cls.pt) | 224 | 78.4 | 94.3 | 232.0 | 1.01 | 57.4 | 154.8 |
- **准确率** 是模型在[ImageNet](https://www.image-net.org/)数据集验证集上的准确度。 - **准确率** 是模型在[ImageNet](https://www.image-net.org/)数据集验证集上的准确度。
<br>通过`yolo val classify data=path/to/ImageNet device=0`复现结果。 <br>通过`yolo val classify data=path/to/ImageNet device=0`复现结果。

10
docs/zh/tasks/detect.md
View File

@ -35,11 +35,11 @@ keywords: YOLOv8, Ultralytics, 目标检测, 预训练模型, 训练, 验证,
| 模型 | 尺寸<br><sup>(像素) | mAP<sup>val<br>50-95 | 速度<br><sup>CPU ONNX<br>(毫秒) | 速度<br><sup>A100 TensorRT<br>(毫秒) | 参数<br><sup>(M) | FLOPs<br><sup>(B) | | 模型 | 尺寸<br><sup>(像素) | mAP<sup>val<br>50-95 | 速度<br><sup>CPU ONNX<br>(毫秒) | 速度<br><sup>A100 TensorRT<br>(毫秒) | 参数<br><sup>(M) | FLOPs<br><sup>(B) |
|--------------------------------------------------------------------------------------|-----------------|----------------------|-----------------------------|----------------------------------|----------------|-------------------| |--------------------------------------------------------------------------------------|-----------------|----------------------|-----------------------------|----------------------------------|----------------|-------------------|
| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 | | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 |
| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 | | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 |
| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 | | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 |
| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 | | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 |
| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 | | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 |
- **mAP<sup>val</sup>** 值适用于 [COCO val2017](http://cocodataset.org) 数据集上的单模型单尺度。 - **mAP<sup>val</sup>** 值适用于 [COCO val2017](http://cocodataset.org) 数据集上的单模型单尺度。
<br>通过 `yolo val detect data=coco.yaml device=0` 复现。 <br>通过 `yolo val detect data=coco.yaml device=0` 复现。

12
docs/zh/tasks/pose.md
View File

@ -35,12 +35,12 @@ keywords: Ultralytics, YOLO, YOLOv8, 姿态估计, 关键点检测, 物体检测
| 模型 | 尺寸<br><sup>(像素) | mAP<sup>姿态<br>50-95 | mAP<sup>姿态<br>50 | 速度<br><sup>CPU ONNX<br>(毫秒) | 速度<br><sup>A100 TensorRT<br>(毫秒) | 参数<br><sup>(M) | 浮点数运算<br><sup>(B) | | 模型 | 尺寸<br><sup>(像素) | mAP<sup>姿态<br>50-95 | mAP<sup>姿态<br>50 | 速度<br><sup>CPU ONNX<br>(毫秒) | 速度<br><sup>A100 TensorRT<br>(毫秒) | 参数<br><sup>(M) | 浮点数运算<br><sup>(B) |
|----------------------------------------------------------------------------------------------------|-----------------|---------------------|------------------|-----------------------------|----------------------------------|----------------|-------------------| |----------------------------------------------------------------------------------------------------|-----------------|---------------------|------------------|-----------------------------|----------------------------------|----------------|-------------------|
| [YOLOv8n-姿态](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 | | [YOLOv8n-姿态](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 |
| [YOLOv8s-姿态](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 | | [YOLOv8s-姿态](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 |
| [YOLOv8m-姿态](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 | | [YOLOv8m-姿态](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 |
| [YOLOv8l-姿态](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 | | [YOLOv8l-姿态](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 |
| [YOLOv8x-姿态](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 | | [YOLOv8x-姿态](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 |
| [YOLOv8x-姿态-p6](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 | | [YOLOv8x-姿态-p6](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 |
- **mAP<sup>val</sup>** 值适用于[COCO 关键点 val2017](http://cocodataset.org)数据集上的单模型单尺度。 - **mAP<sup>val</sup>** 值适用于[COCO 关键点 val2017](http://cocodataset.org)数据集上的单模型单尺度。
<br>通过执行 `yolo val pose data=coco-pose.yaml device=0` 来复现。 <br>通过执行 `yolo val pose data=coco-pose.yaml device=0` 来复现。

10
docs/zh/tasks/segment.md
View File

@ -35,11 +35,11 @@ keywords: yolov8, 实例分割, Ultralytics, COCO数据集, 图像分割, 物体
| 模型 | 尺寸<br><sup>(像素) | mAP<sup>box<br>50-95 | mAP<sup>mask<br>50-95 | 速度<br><sup>CPU ONNX<br>(ms) | 速度<br><sup>A100 TensorRT<br>(ms) | 参数<br><sup>(M) | FLOPs<br><sup>(B) | | 模型 | 尺寸<br><sup>(像素) | mAP<sup>box<br>50-95 | mAP<sup>mask<br>50-95 | 速度<br><sup>CPU ONNX<br>(ms) | 速度<br><sup>A100 TensorRT<br>(ms) | 参数<br><sup>(M) | FLOPs<br><sup>(B) |
|----------------------------------------------------------------------------------------------|-----------------|----------------------|-----------------------|-----------------------------|----------------------------------|----------------|-------------------| |----------------------------------------------------------------------------------------------|-----------------|----------------------|-----------------------|-----------------------------|----------------------------------|----------------|-------------------|
| [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 | | [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 |
| [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 | | [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 |
| [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 | | [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 |
| [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 | | [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 |
| [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 | | [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 |
- **mAP<sup>val</sup>** 值针对[COCO val2017](http://cocodataset.org)数据集的单模型单尺度。 - **mAP<sup>val</sup>** 值针对[COCO val2017](http://cocodataset.org)数据集的单模型单尺度。
<br>通过`yolo val segment data=coco.yaml device=0`复现。 <br>通过`yolo val segment data=coco.yaml device=0`复现。

2
examples/YOLOv8-ONNXRuntime-CPP/inference.cpp
View File

@ -240,7 +240,7 @@ char* YOLO_V8::TensorProcess(clock_t& starttime_1, cv::Mat& iImg, N& blob, std::
} }
//Note: //Note:
//ultralytics add transpose operator to the output of yolov8 model.which make yolov8/v5/v7 has same shape //ultralytics add transpose operator to the output of yolov8 model.which make yolov8/v5/v7 has same shape
//https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt //https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt
//rowData = rowData.t(); //rowData = rowData.t();
float* data = (float*)rawData.data; float* data = (float*)rawData.data;

26
examples/YOLOv8-Region-Counter/yolov8_region_counter.py
View File

@ -35,7 +35,31 @@ counting_regions = [
def mouse_callback(event, x, y, flags, param): def mouse_callback(event, x, y, flags, param):
"""Mouse call back event.""" """
Handles mouse events for region manipulation.
Parameters:
event (int): The mouse event type (e.g., cv2.EVENT_LBUTTONDOWN).
x (int): The x-coordinate of the mouse pointer.
y (int): The y-coordinate of the mouse pointer.
flags (int): Additional flags passed by OpenCV.
param: Additional parameters passed to the callback (not used in this function).
Global Variables:
current_region (dict): A dictionary representing the current selected region.
Mouse Events:
- LBUTTONDOWN: Initiates dragging for the region containing the clicked point.
- MOUSEMOVE: Moves the selected region if dragging is active.
- LBUTTONUP: Ends dragging for the selected region.
Notes:
- This function is intended to be used as a callback for OpenCV mouse events.
- Requires the existence of the 'counting_regions' list and the 'Polygon' class.
Example:
>>> cv2.setMouseCallback(window_name, mouse_callback)
"""
global current_region global current_region
# Mouse left button down event # Mouse left button down event

2
examples/tutorial.ipynb
View File

@ -107,7 +107,7 @@
"output_type": "stream", "output_type": "stream",
"name": "stdout", "name": "stdout",
"text": [ "text": [
"Downloading https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt to 'yolov8n.pt'...\n", "Downloading https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt to 'yolov8n.pt'...\n",
"100% 6.23M/6.23M [00:00<00:00, 77.2MB/s]\n", "100% 6.23M/6.23M [00:00<00:00, 77.2MB/s]\n",
"Ultralytics YOLOv8.0.145 🚀 Python-3.10.6 torch-2.0.1+cu118 CUDA:0 (Tesla T4, 15102MiB)\n", "Ultralytics YOLOv8.0.145 🚀 Python-3.10.6 torch-2.0.1+cu118 CUDA:0 (Tesla T4, 15102MiB)\n",
"YOLOv8n summary (fused): 168 layers, 3151904 parameters, 0 gradients\n", "YOLOv8n summary (fused): 168 layers, 3151904 parameters, 0 gradients\n",

2
tests/test_integrations.py
View File

@ -93,7 +93,7 @@ def test_pycocotools():
from ultralytics.models.yolo.segment import SegmentationValidator from ultralytics.models.yolo.segment import SegmentationValidator
# Download annotations after each dataset downloads first # Download annotations after each dataset downloads first
url = 'https://github.com/ultralytics/assets/releases/download/v0.0.0/' url = 'https://github.com/ultralytics/assets/releases/download/v8.1.0/'
args = {'model': 'yolov8n.pt', 'data': 'coco8.yaml', 'save_json': True, 'imgsz': 64} args = {'model': 'yolov8n.pt', 'data': 'coco8.yaml', 'save_json': True, 'imgsz': 64}
validator = DetectionValidator(args=args) validator = DetectionValidator(args=args)

2
ultralytics/__init__.py
View File

@ -1,6 +1,6 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license # Ultralytics YOLO 🚀, AGPL-3.0 license
__version__ = "8.0.239" __version__ = "8.1.0"
from ultralytics.data.explorer.explorer import Explorer from ultralytics.data.explorer.explorer import Explorer
from ultralytics.models import RTDETR, SAM, YOLO from ultralytics.models import RTDETR, SAM, YOLO

8
ultralytics/engine/predictor.py
View File

@ -262,9 +262,13 @@ class BasePredictor:
self.model.warmup(imgsz=(1 if self.model.pt or self.model.triton else self.dataset.bs, 3, *self.imgsz)) self.model.warmup(imgsz=(1 if self.model.pt or self.model.triton else self.dataset.bs, 3, *self.imgsz))
self.done_warmup = True self.done_warmup = True
self.seen, self.windows, self.batch, profilers = 0, [], None, (ops.Profile(), ops.Profile(), ops.Profile()) self.seen, self.windows, self.batch = 0, [], None
profilers = (
ops.Profile(device=self.device),
ops.Profile(device=self.device),
ops.Profile(device=self.device),
)
self.run_callbacks("on_predict_start") self.run_callbacks("on_predict_start")
for batch in self.dataset: for batch in self.dataset:
self.run_callbacks("on_predict_batch_start") self.run_callbacks("on_predict_batch_start")
self.batch = batch self.batch = batch

7
ultralytics/engine/validator.py
View File

@ -155,7 +155,12 @@ class BaseValidator:
model.warmup(imgsz=(1 if pt else self.args.batch, 3, imgsz, imgsz)) # warmup model.warmup(imgsz=(1 if pt else self.args.batch, 3, imgsz, imgsz)) # warmup
self.run_callbacks("on_val_start") self.run_callbacks("on_val_start")
dt = Profile(), Profile(), Profile(), Profile() dt = (
Profile(device=self.device),
Profile(device=self.device),
Profile(device=self.device),
Profile(device=self.device),
)
bar = TQDM(self.dataloader, desc=self.get_desc(), total=len(self.dataloader)) bar = TQDM(self.dataloader, desc=self.get_desc(), total=len(self.dataloader))
self.init_metrics(de_parallel(model)) self.init_metrics(de_parallel(model))
self.jdict = [] # empty before each val self.jdict = [] # empty before each val

4
ultralytics/utils/downloads.py
View File

@ -397,7 +397,7 @@ def get_github_assets(repo="ultralytics/assets", version="latest", retry=False):
return data["tag_name"], [x["name"] for x in data["assets"]] # tag, assets i.e. ['yolov8n.pt', 'yolov8s.pt', ...] return data["tag_name"], [x["name"] for x in data["assets"]] # tag, assets i.e. ['yolov8n.pt', 'yolov8s.pt', ...]
def attempt_download_asset(file, repo="ultralytics/assets", release="v0.0.0", **kwargs): def attempt_download_asset(file, repo="ultralytics/assets", release="v8.1.0", **kwargs):
""" """
Attempt to download a file from GitHub release assets if it is not found locally. The function checks for the file Attempt to download a file from GitHub release assets if it is not found locally. The function checks for the file
locally first, then tries to download it from the specified GitHub repository release. locally first, then tries to download it from the specified GitHub repository release.
@ -405,7 +405,7 @@ def attempt_download_asset(file, repo="ultralytics/assets", release="v0.0.0", **
Args: Args:
file (str | Path): The filename or file path to be downloaded. file (str | Path): The filename or file path to be downloaded.
repo (str, optional): The GitHub repository in the format 'owner/repo'. Defaults to 'ultralytics/assets'. repo (str, optional): The GitHub repository in the format 'owner/repo'. Defaults to 'ultralytics/assets'.
release (str, optional): The specific release version to be downloaded. Defaults to 'v0.0.0'. release (str, optional): The specific release version to be downloaded. Defaults to 'v8.1.0'.
**kwargs (dict): Additional keyword arguments for the download process. **kwargs (dict): Additional keyword arguments for the download process.
Returns: Returns:

10
ultralytics/utils/ops.py
View File

@ -23,22 +23,24 @@ class Profile(contextlib.ContextDecorator):
```python ```python
from ultralytics.utils.ops import Profile from ultralytics.utils.ops import Profile
with Profile() as dt: with Profile(device=device) as dt:
pass # slow operation here pass # slow operation here
print(dt) # prints "Elapsed time is 9.5367431640625e-07 s" print(dt) # prints "Elapsed time is 9.5367431640625e-07 s"
``` ```
""" """
def __init__(self, t=0.0): def __init__(self, t=0.0, device: torch.device = None):
""" """
Initialize the Profile class. Initialize the Profile class.
Args: Args:
t (float): Initial time. Defaults to 0.0. t (float): Initial time. Defaults to 0.0.
device (torch.device): Devices used for model inference. Defaults to None (cpu).
""" """
self.t = t self.t = t
self.cuda = torch.cuda.is_available() self.device = device
self.cuda = True if (device and str(device)[:4] == "cuda") else False
def __enter__(self): def __enter__(self):
"""Start timing.""" """Start timing."""
@ -57,7 +59,7 @@ class Profile(contextlib.ContextDecorator):
def time(self): def time(self):
"""Get current time.""" """Get current time."""
if self.cuda: if self.cuda:
torch.cuda.synchronize() torch.cuda.synchronize(self.device)
return time.time() return time.time()