diff --git a/README.md b/README.md index 551b7e76..0e1ccf80 100644 --- a/README.md +++ b/README.md @@ -191,17 +191,15 @@ See [Pose Docs](https://docs.ultralytics.com/tasks/pose/) for usage examples wit See [Obb Docs](https://docs.ultralytics.com/tasks/obb/) for usage examples with these models trained on [DOTAv1](https://docs.ultralytics.com/datasets/obb/dota-v2/#dota-v10/), which include 15 pre-trained classes. -| Model | size
(pixels) | mAPbox
50 | Speed
CPU ONNX
(ms) | Speed
A100 TensorRT
(ms) | params
(M) | FLOPs
(B) | -| -------------------------------------------------------------------------------------------- | --------------------- | ----------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- | -| [YOLOv8n-obb](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-obb.pt) | 1024 | \<++> | \<++> | \<++> | 3.2 | 23.3 | -| [YOLOv8s-obb](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-obb.pt) | 1024 | \<++> | \<++> | \<++> | 11.4 | 76.3 | -| [YOLOv8m-obb](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-obb.pt) | 1024 | \<++> | \<++> | \<++> | 26.4 | 208.6 | -| [YOLOv8l-obb](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-obb.pt) | 1024 | \<++> | \<++> | \<++> | 44.5 | 433.8 | -| [YOLOv8x-obb](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-obb.pt) | 1024 | \<++> | \<++> | \<++> | 69.5 | 676.7 | +| Model | size
(pixels) | mAPtest
50 | Speed
CPU ONNX
(ms) | Speed
A100 TensorRT
(ms) | params
(M) | FLOPs
(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 | +| [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 | +| [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 | +| [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 | +| [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 | - - -- **mAPval** values are for single-model single-scale on [DOTAv1](https://captain-whu.github.io/DOTA/index.html) dataset.
Reproduce by `yolo val obb data=DOTAv1.yaml device=0` +- **mAPtest** values are for single-model multi-scale on [DOTAv1](https://captain-whu.github.io/DOTA/index.html) dataset.
Reproduce by `yolo val obb data=DOTAv1.yaml device=0 split=test` - **Speed** averaged over DOTAv1 val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance.
Reproduce by `yolo val obb data=DOTAv1.yaml batch=1 device=0|cpu` diff --git a/README.zh-CN.md b/README.zh-CN.md index 225a7789..f6df660e 100644 --- a/README.zh-CN.md +++ b/README.zh-CN.md @@ -193,15 +193,15 @@ Ultralytics 提供了 YOLOv8 的交互式笔记本，涵盖训练、验证、跟 查看[旋转检测文档](https://docs.ultralytics.com/tasks/obb/)以获取这些在[DOTAv1](https://docs.ultralytics.com/datasets/obb/dota-v2/#dota-v10/)上训练的模型的使用示例，其中包括15个预训练类别。 -| 模型 | 尺寸
(像素) | mAPpose
50 | 速度
CPU ONNX
(ms) | 速度
A100 TensorRT
(ms) | 参数
(M) | FLOPs
(B) | +| 模型 | 尺寸
(像素) | mAPtest
50 | 速度
CPU ONNX
(ms) | 速度
A100 TensorRT
(ms) | 参数
(M) | FLOPs
(B) | | -------------------------------------------------------------------------------------------- | --------------- | ------------------ | --------------------------- | -------------------------------- | -------------- | ----------------- | -| [YOLOv8n-obb](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-obb.pt) | 1024 | \<++> | \<++> | 3.2 | 23.3 | | -| [YOLOv8s-obb](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-obb.pt) | 1024 | \<++> | \<++> | 11.4 | 76.3 | | -| [YOLOv8m-obb](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-obb.pt) | 1024 | \<++> | \<++> | 26.4 | 208.6 | | -| [YOLOv8l-obb](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-obb.pt) | 1024 | \<++> | \<++> | 44.5 | 433.8 | | -| [YOLOv8x-obb](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-obb.pt) | 1024 | \<++> | \<++> | 69.5 | 676.7 | | +| [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 | +| [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 | +| [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 | +| [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 | +| [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 | -- **mAPval** 值是基于单模型单尺度在 [DOTAv1](https://captain-whu.github.io/DOTA/index.html) 数据集上的结果。
通过 `yolo val obb data=DOTAv1.yaml device=0` 复现 +- **mAPval** 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。
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。
通过 `yolo val obb data=DOTAv1.yaml batch=1 device=0|cpu` 复现 diff --git a/docs/en/models/yolov8.md b/docs/en/models/yolov8.md index 01c499f5..dba33d4d 100644 --- a/docs/en/models/yolov8.md +++ b/docs/en/models/yolov8.md @@ -115,13 +115,13 @@ This table provides an overview of the YOLOv8 model variants, highlighting their See [Oriented Detection Docs](https://docs.ultralytics.com/tasks/obb/) for usage examples with these models trained on [DOTAv1](https://docs.ultralytics.com/datasets/obb/dota-v2/#dota-v10/), which include 15 pre-trained classes. - | Model | size
(pixels) | mAPbox
50 | Speed
CPU ONNX
(ms) | Speed
A100 TensorRT
(ms) | params
(M) | FLOPs
(B) | - |----------------------------------------------------------------------------------------------|-----------------------|-------------------|--------------------------------|-------------------------------------|--------------------|-------------------| - | [YOLOv8n-obb](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-obb.pt) | 1024 | <++> | <++> | <++> | 3.2 | 23.3 | - | [YOLOv8s-obb](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-obb.pt) | 1024 | <++> | <++> | <++> | 11.4 | 76.3 | - | [YOLOv8m-obb](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-obb.pt) | 1024 | <++> | <++> | <++> | 26.4 | 208.6 | - | [YOLOv8l-obb](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-obb.pt) | 1024 | <++> | <++> | <++> | 44.5 | 433.8 | - | [YOLOv8x-obb](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-obb.pt) | 1024 | <++> | <++> | <++> | 69.5 | 676.7 | + | Model | size
(pixels) | mAPtest
50 | Speed
CPU ONNX
(ms) | Speed
A100 TensorRT
(ms) | params
(M) | FLOPs
(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 | + | [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 | + | [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 | + | [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 | + | [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 | ## Usage Examples diff --git a/docs/en/tasks/obb.md b/docs/en/tasks/obb.md index 1753c64b..de979239 100644 --- a/docs/en/tasks/obb.md +++ b/docs/en/tasks/obb.md @@ -4,7 +4,7 @@ description: Learn how to use oriented object detection models with Ultralytics keywords: yolov8, oriented object detection, Ultralytics, DOTA dataset, rotated object detection, object detection, model training, model validation, image prediction, model export --- -# Oriented Object Detection +# Oriented Bounding Boxes Object Detection @@ -24,17 +24,15 @@ YOLOv8 pretrained Obb models are shown here, which are pretrained on the [DOTAv1 [Models](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/cfg/models) download automatically from the latest Ultralytics [release](https://github.com/ultralytics/assets/releases) on first use. -| Model | size
(pixels) | mAPbox
50 | Speed
CPU ONNX
(ms) | Speed
A100 TensorRT
(ms) | params
(M) | FLOPs
(B) | -|----------------------------------------------------------------------------------------------|-----------------------|-------------------|--------------------------------|-------------------------------------|--------------------|-------------------| -| [YOLOv8n-obb](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-obb.pt) | 1024 | <++> | <++> | <++> | 3.2 | 23.3 | -| [YOLOv8s-obb](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-obb.pt) | 1024 | <++> | <++> | <++> | 11.4 | 76.3 | -| [YOLOv8m-obb](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-obb.pt) | 1024 | <++> | <++> | <++> | 26.4 | 208.6 | -| [YOLOv8l-obb](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-obb.pt) | 1024 | <++> | <++> | <++> | 44.5 | 433.8 | -| [YOLOv8x-obb](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-obb.pt) | 1024 | <++> | <++> | <++> | 69.5 | 676.7 | +| Model | size
(pixels) | mAPtest
50 | Speed
CPU ONNX
(ms) | Speed
A100 TensorRT
(ms) | params
(M) | FLOPs
(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 | +| [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 | +| [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 | +| [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 | +| [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 | - - -- **mAPval** values are for single-model single-scale on [DOTAv1 test](http://cocodataset.org) dataset.
Reproduce by `yolo val obb data=DOTAv1.yaml device=0` +- **mAPtest** values are for single-model multi-scale on [DOTAv1 test](http://cocodataset.org) dataset.
Reproduce by `yolo val obb data=DOTAv1.yaml device=0 split=test` - **Speed** averaged over DOTAv1 val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance.
Reproduce by `yolo val obb data=DOTAv1.yaml batch=1 device=0|cpu` ## Train diff --git a/examples/YOLOv8-ONNXRuntime-CPP/README.md b/examples/YOLOv8-ONNXRuntime-CPP/README.md index 435bc571..1cb6eb3d 100644 --- a/examples/YOLOv8-ONNXRuntime-CPP/README.md +++ b/examples/YOLOv8-ONNXRuntime-CPP/README.md @@ -1,7 +1,6 @@ # YOLOv8 OnnxRuntime C++ -C++ -Onnx-runtime +C++ Onnx-runtime This example demonstrates how to perform inference using YOLOv8 in C++ with ONNX Runtime and OpenCV's API. @@ -11,7 +10,7 @@ This example demonstrates how to perform inference using YOLOv8 in C++ with ONNX - Faster than OpenCV's DNN inference on both CPU and GPU. - Supports FP32 and FP16 CUDA acceleration. -## Note :coffee: +## Note ☕ 1. Benefit for Ultralytics' latest release, a `Transpose` op is added to the YOLOv8 model, while make v8 and v5 has the same output shape. Therefore, you can run inference with YOLOv5/v7/v8 via this project.