diff --git a/README.md b/README.md index 0c61bc2c..578fdc2e 100644 --- a/README.md +++ b/README.md @@ -177,7 +177,7 @@ See [Pose Docs](https://docs.ultralytics.com/tasks/pose/) for usage examples wit
Obb (DOTAv1) -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-v1), which include 15 pre-trained classes. +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) | | -------------------------------------------------------------------------------------------- | --------------------- | ----------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- | diff --git a/README.zh-CN.md b/README.zh-CN.md index 4dbe2e56..a85dd79a 100644 --- a/README.zh-CN.md +++ b/README.zh-CN.md @@ -177,7 +177,7 @@ success = model.export(format="onnx") # 将模型导出为 ONNX 格式
旋转检测 (DOTAv1) -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-v1/)上训练的模型的使用示例，其中包括15个预训练类别。 +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) | | -------------------------------------------------------------------------------------------- | --------------- | ------------------ | --------------------------- | -------------------------------- | -------------- | ----------------- | diff --git a/docs/en/datasets/obb/dota-v2.md b/docs/en/datasets/obb/dota-v2.md index 48087f4b..81e9a398 100644 --- a/docs/en/datasets/obb/dota-v2.md +++ b/docs/en/datasets/obb/dota-v2.md @@ -1,14 +1,14 @@ --- comments: true -description: Delve into DOTA v2, an Oriented Bounding Box (OBB) aerial imagery dataset with 1.7 million instances and 11,268 images. -keywords: DOTA v2, object detection, aerial images, computer vision, deep learning, annotations, oriented bounding boxes, OBB +description: Delve into DOTA, an Oriented Bounding Box (OBB) aerial imagery dataset with 1.7 million instances and 11,268 images. +keywords: DOTA v1, DOTA v1.5, DOTA v2, object detection, aerial images, computer vision, deep learning, annotations, oriented bounding boxes, OBB --- -# DOTA v2 Dataset with OBB +# DOTA Dataset with OBB -[DOTA v2](https://captain-whu.github.io/DOTA/index.html) stands as a specialized dataset, emphasizing object detection in aerial images. Originating from the DOTA series of datasets, it offers annotated images capturing a diverse array of aerial scenes with Oriented Bounding Boxes (OBB). +[DOTA](https://captain-whu.github.io/DOTA/index.html) stands as a specialized dataset, emphasizing object detection in aerial images. Originating from the DOTA series of datasets, it offers annotated images capturing a diverse array of aerial scenes with Oriented Bounding Boxes (OBB). -![DOTA v2 classes visual](https://user-images.githubusercontent.com/26833433/259461765-72fdd0d8-266b-44a9-8199-199329bf5ca9.jpg) +![DOTA classes visual](https://user-images.githubusercontent.com/26833433/259461765-72fdd0d8-266b-44a9-8199-199329bf5ca9.jpg) ## Key Features @@ -47,28 +47,28 @@ keywords: DOTA v2, object detection, aerial images, computer vision, deep learni ## Dataset Structure -DOTA v2 exhibits a structured layout tailored for OBB object detection challenges: +DOTA exhibits a structured layout tailored for OBB object detection challenges: - **Images**: A vast collection of high-resolution aerial images capturing diverse terrains and structures. - **Oriented Bounding Boxes**: Annotations in the form of rotated rectangles encapsulating objects irrespective of their orientation, ideal for capturing objects like airplanes, ships, and buildings. ## Applications -DOTA v2 serves as a benchmark for training and evaluating models specifically tailored for aerial image analysis. With the inclusion of OBB annotations, it provides a unique challenge, enabling the development of specialized object detection models that cater to aerial imagery's nuances. +DOTA serves as a benchmark for training and evaluating models specifically tailored for aerial image analysis. With the inclusion of OBB annotations, it provides a unique challenge, enabling the development of specialized object detection models that cater to aerial imagery's nuances. ## Dataset YAML -Typically, datasets incorporate a YAML (Yet Another Markup Language) file detailing the dataset's configuration. For DOTA v2, a hypothetical `DOTAv2.yaml` could be used. For accurate paths and configurations, it's vital to consult the dataset's official repository or documentation. +Typically, datasets incorporate a YAML (Yet Another Markup Language) file detailing the dataset's configuration. For DOTA v1 and DOTA v1.5, Ultralytics provides `DOTAv1.yaml` and `DOTAv1.5.yaml` files. For additional details on these as well as DOTA v2 please consult DOTA's official repository and documentation. -!!! Example "DOTAv2.yaml" +!!! Example "DOTAv1.yaml" ```yaml - --8<-- "ultralytics/cfg/datasets/DOTAv2.yaml" + --8<-- "ultralytics/cfg/datasets/DOTAv1.yaml" ``` ## Usage -To train a model on the DOTA v2 dataset, you can utilize the following code snippets. Always refer to your model's documentation for a thorough list of available arguments. +To train a model on the DOTA v1 dataset, you can utilize the following code snippets. Always refer to your model's documentation for a thorough list of available arguments. !!! Warning @@ -85,14 +85,14 @@ To train a model on the DOTA v2 dataset, you can utilize the following code snip model = YOLO('yolov8n-obb.yaml') # Train the model on the DOTAv2 dataset - results = model.train(data='DOTAv2.yaml', epochs=100, imgsz=640) + results = model.train(data='DOTAv1.yaml', epochs=100, imgsz=640) ``` === "CLI" ```bash # Train a new YOLOv8n-OBB model on the DOTAv2 dataset - yolo detect train data=DOTAv2.yaml model=yolov8n.pt epochs=100 imgsz=640 + yolo detect train data=DOTAv1.yaml model=yolov8n.pt epochs=100 imgsz=640 ``` ## Sample Data and Annotations @@ -101,13 +101,13 @@ Having a glance at the dataset illustrates its depth: ![Dataset sample image](https://captain-whu.github.io/DOTA/images/instances-DOTA.jpg) -- **DOTA v2**: This snapshot underlines the complexity of aerial scenes and the significance of Oriented Bounding Box annotations, capturing objects in their natural orientation. +- **DOTA examples**: This snapshot underlines the complexity of aerial scenes and the significance of Oriented Bounding Box annotations, capturing objects in their natural orientation. The dataset's richness offers invaluable insights into object detection challenges exclusive to aerial imagery. ## Citations and Acknowledgments -For those leveraging DOTA v2 in their endeavors, it's pertinent to cite the relevant research papers: +For those leveraging DOTA in their endeavors, it's pertinent to cite the relevant research papers: !!! Quote "" @@ -126,4 +126,4 @@ For those leveraging DOTA v2 in their endeavors, it's pertinent to cite the rele } ``` -A special note of gratitude to the team behind DOTA v2 for their commendable effort in curating this dataset. For an exhaustive understanding of the dataset and its nuances, please visit the [official DOTA v2 website](https://captain-whu.github.io/DOTA/index.html). +A special note of gratitude to the team behind the DOTA datasets for their commendable effort in curating this dataset. For an exhaustive understanding of the dataset and its nuances, please visit the [official DOTA website](https://captain-whu.github.io/DOTA/index.html). diff --git a/docs/en/datasets/obb/index.md b/docs/en/datasets/obb/index.md index 9fa79e9b..fe1d7aac 100644 --- a/docs/en/datasets/obb/index.md +++ b/docs/en/datasets/obb/index.md @@ -43,14 +43,14 @@ To train a model using these OBB formats: model = YOLO('yolov8n-obb.yaml') # Train the model on the DOTAv2 dataset - results = model.train(data='DOTAv2.yaml', epochs=100, imgsz=640) + results = model.train(data='DOTAv1.yaml', epochs=100, imgsz=640) ``` === "CLI" ```bash # Train a new YOLOv8n-OBB model on the DOTAv2 dataset - yolo detect train data=DOTAv2.yaml model=yolov8n.pt epochs=100 imgsz=640 + yolo detect train data=DOTAv1.yaml model=yolov8n.pt epochs=100 imgsz=640 ``` ## Supported Datasets diff --git a/docs/en/models/yolov8.md b/docs/en/models/yolov8.md index 8c34f5e8..6606f573 100644 --- a/docs/en/models/yolov8.md +++ b/docs/en/models/yolov8.md @@ -113,7 +113,7 @@ This table provides an overview of the YOLOv8 model variants, highlighting their === "OBB (DOTAv1)" - 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-v1/), which include 15 pre-trained classes. + 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) | |----------------------------------------------------------------------------------------------|-----------------------|-------------------|--------------------------------|-------------------------------------|--------------------|-------------------| diff --git a/ultralytics/cfg/datasets/Argoverse.yaml b/ultralytics/cfg/datasets/Argoverse.yaml index 76255e4b..52f4e79d 100644 --- a/ultralytics/cfg/datasets/Argoverse.yaml +++ b/ultralytics/cfg/datasets/Argoverse.yaml @@ -1,5 +1,6 @@ # Ultralytics YOLO 🚀, AGPL-3.0 license # Argoverse-HD dataset (ring-front-center camera) http://www.cs.cmu.edu/~mengtial/proj/streaming/ by Argo AI +# Documentation: https://docs.ultralytics.com/datasets/detect/argoverse/ # Example usage: yolo train data=Argoverse.yaml # parent # ├── ultralytics diff --git a/ultralytics/cfg/datasets/DOTAv1.5.yaml b/ultralytics/cfg/datasets/DOTAv1.5.yaml index 39f89a00..1480ad0f 100644 --- a/ultralytics/cfg/datasets/DOTAv1.5.yaml +++ b/ultralytics/cfg/datasets/DOTAv1.5.yaml @@ -1,6 +1,7 @@ # Ultralytics YOLO 🚀, AGPL-3.0 license # DOTA 1.5 dataset https://captain-whu.github.io/DOTA/index.html for object detection in aerial images by Wuhan University -# Example usage: yolo train model=yolov8n-obb.pt data=DOTAv2.yaml +# Documentation: https://docs.ultralytics.com/datasets/obb/dota-v2/ +# Example usage: yolo train model=yolov8n-obb.pt data=DOTAv1.5.yaml # parent # ├── ultralytics # └── datasets diff --git a/ultralytics/cfg/datasets/DOTAv1.yaml b/ultralytics/cfg/datasets/DOTAv1.yaml index bdec4925..fa134048 100644 --- a/ultralytics/cfg/datasets/DOTAv1.yaml +++ b/ultralytics/cfg/datasets/DOTAv1.yaml @@ -1,6 +1,7 @@ # Ultralytics YOLO 🚀, AGPL-3.0 license # DOTA 1.0 dataset https://captain-whu.github.io/DOTA/index.html for object detection in aerial images by Wuhan University -# Example usage: yolo train model=yolov8n-obb.pt data=DOTAv2.yaml +# Documentation: https://docs.ultralytics.com/datasets/obb/dota-v2/ +# Example usage: yolo train model=yolov8n-obb.pt data=DOTAv1.yaml # parent # ├── ultralytics # └── datasets diff --git a/ultralytics/cfg/datasets/GlobalWheat2020.yaml b/ultralytics/cfg/datasets/GlobalWheat2020.yaml index 165004f6..9d47bfe4 100644 --- a/ultralytics/cfg/datasets/GlobalWheat2020.yaml +++ b/ultralytics/cfg/datasets/GlobalWheat2020.yaml @@ -1,5 +1,6 @@ # Ultralytics YOLO 🚀, AGPL-3.0 license # Global Wheat 2020 dataset http://www.global-wheat.com/ by University of Saskatchewan +# Documentation: https://docs.ultralytics.com/datasets/detect/globalwheat2020/ # Example usage: yolo train data=GlobalWheat2020.yaml # parent # ├── ultralytics diff --git a/ultralytics/cfg/datasets/ImageNet.yaml b/ultralytics/cfg/datasets/ImageNet.yaml index c1aa155f..fbdb9aa1 100644 --- a/ultralytics/cfg/datasets/ImageNet.yaml +++ b/ultralytics/cfg/datasets/ImageNet.yaml @@ -1,6 +1,7 @@ # Ultralytics YOLO 🚀, AGPL-3.0 license # ImageNet-1k dataset https://www.image-net.org/index.php by Stanford University # Simplified class names from https://github.com/anishathalye/imagenet-simple-labels +# Documentation: https://docs.ultralytics.com/datasets/classify/imagenet/ # Example usage: yolo train task=classify data=imagenet # parent # ├── ultralytics diff --git a/ultralytics/cfg/datasets/Objects365.yaml b/ultralytics/cfg/datasets/Objects365.yaml index 415eff98..6d38f4d2 100644 --- a/ultralytics/cfg/datasets/Objects365.yaml +++ b/ultralytics/cfg/datasets/Objects365.yaml @@ -1,5 +1,6 @@ # Ultralytics YOLO 🚀, AGPL-3.0 license # Objects365 dataset https://www.objects365.org/ by Megvii +# Documentation: https://docs.ultralytics.com/datasets/detect/objects365/ # Example usage: yolo train data=Objects365.yaml # parent # ├── ultralytics diff --git a/ultralytics/cfg/datasets/SKU-110K.yaml b/ultralytics/cfg/datasets/SKU-110K.yaml index e6deac21..19c1635b 100644 --- a/ultralytics/cfg/datasets/SKU-110K.yaml +++ b/ultralytics/cfg/datasets/SKU-110K.yaml @@ -1,5 +1,6 @@ # Ultralytics YOLO 🚀, AGPL-3.0 license # SKU-110K retail items dataset https://github.com/eg4000/SKU110K_CVPR19 by Trax Retail +# Documentation: https://docs.ultralytics.com/datasets/detect/sku-110k/ # Example usage: yolo train data=SKU-110K.yaml # parent # ├── ultralytics diff --git a/ultralytics/cfg/datasets/VOC.yaml b/ultralytics/cfg/datasets/VOC.yaml index f4e156d7..6f76c632 100644 --- a/ultralytics/cfg/datasets/VOC.yaml +++ b/ultralytics/cfg/datasets/VOC.yaml @@ -1,5 +1,6 @@ # Ultralytics YOLO 🚀, AGPL-3.0 license # PASCAL VOC dataset http://host.robots.ox.ac.uk/pascal/VOC by University of Oxford +# Documentation: # Documentation: https://docs.ultralytics.com/datasets/detect/voc/ # Example usage: yolo train data=VOC.yaml # parent # ├── ultralytics diff --git a/ultralytics/cfg/datasets/VisDrone.yaml b/ultralytics/cfg/datasets/VisDrone.yaml index a1a4a466..c483d9b4 100644 --- a/ultralytics/cfg/datasets/VisDrone.yaml +++ b/ultralytics/cfg/datasets/VisDrone.yaml @@ -1,5 +1,6 @@ # Ultralytics YOLO 🚀, AGPL-3.0 license # VisDrone2019-DET dataset https://github.com/VisDrone/VisDrone-Dataset by Tianjin University +# Documentation: https://docs.ultralytics.com/datasets/detect/visdrone/ # Example usage: yolo train data=VisDrone.yaml # parent # ├── ultralytics diff --git a/ultralytics/cfg/datasets/coco-pose.yaml b/ultralytics/cfg/datasets/coco-pose.yaml index 670d55bf..0b72d86c 100644 --- a/ultralytics/cfg/datasets/coco-pose.yaml +++ b/ultralytics/cfg/datasets/coco-pose.yaml @@ -1,5 +1,6 @@ # Ultralytics YOLO 🚀, AGPL-3.0 license # COCO 2017 dataset http://cocodataset.org by Microsoft +# Documentation: https://docs.ultralytics.com/datasets/pose/coco/ # Example usage: yolo train data=coco-pose.yaml # parent # ├── ultralytics diff --git a/ultralytics/cfg/datasets/coco.yaml b/ultralytics/cfg/datasets/coco.yaml index 8a70a5b3..3febd5f2 100644 --- a/ultralytics/cfg/datasets/coco.yaml +++ b/ultralytics/cfg/datasets/coco.yaml @@ -1,5 +1,6 @@ # Ultralytics YOLO 🚀, AGPL-3.0 license # COCO 2017 dataset http://cocodataset.org by Microsoft +# Documentation: https://docs.ultralytics.com/datasets/detect/coco/ # Example usage: yolo train data=coco.yaml # parent # ├── ultralytics diff --git a/ultralytics/cfg/datasets/coco128-seg.yaml b/ultralytics/cfg/datasets/coco128-seg.yaml index 8c2e3da3..176d5126 100644 --- a/ultralytics/cfg/datasets/coco128-seg.yaml +++ b/ultralytics/cfg/datasets/coco128-seg.yaml @@ -1,5 +1,6 @@ # Ultralytics YOLO 🚀, AGPL-3.0 license # COCO128-seg dataset https://www.kaggle.com/ultralytics/coco128 (first 128 images from COCO train2017) by Ultralytics +# Documentation: https://docs.ultralytics.com/datasets/segment/coco/ # Example usage: yolo train data=coco128.yaml # parent # ├── ultralytics diff --git a/ultralytics/cfg/datasets/coco128.yaml b/ultralytics/cfg/datasets/coco128.yaml index 9749ab6c..a66cbe50 100644 --- a/ultralytics/cfg/datasets/coco128.yaml +++ b/ultralytics/cfg/datasets/coco128.yaml @@ -1,5 +1,6 @@ # Ultralytics YOLO 🚀, AGPL-3.0 license # COCO128 dataset https://www.kaggle.com/ultralytics/coco128 (first 128 images from COCO train2017) by Ultralytics +# Documentation: https://docs.ultralytics.com/datasets/detect/coco/ # Example usage: yolo train data=coco128.yaml # parent # ├── ultralytics diff --git a/ultralytics/cfg/datasets/coco8-pose.yaml b/ultralytics/cfg/datasets/coco8-pose.yaml index e6fab8b5..dcb6424b 100644 --- a/ultralytics/cfg/datasets/coco8-pose.yaml +++ b/ultralytics/cfg/datasets/coco8-pose.yaml @@ -1,5 +1,6 @@ # Ultralytics YOLO 🚀, AGPL-3.0 license # COCO8-pose dataset (first 8 images from COCO train2017) by Ultralytics +# Documentation: https://docs.ultralytics.com/datasets/pose/coco8-pose/ # Example usage: yolo train data=coco8-pose.yaml # parent # ├── ultralytics diff --git a/ultralytics/cfg/datasets/coco8-seg.yaml b/ultralytics/cfg/datasets/coco8-seg.yaml index e6faca1c..1f54a233 100644 --- a/ultralytics/cfg/datasets/coco8-seg.yaml +++ b/ultralytics/cfg/datasets/coco8-seg.yaml @@ -1,5 +1,6 @@ # Ultralytics YOLO 🚀, AGPL-3.0 license # COCO8-seg dataset (first 8 images from COCO train2017) by Ultralytics +# Documentation: https://docs.ultralytics.com/datasets/segment/coco8-seg/ # Example usage: yolo train data=coco8-seg.yaml # parent # ├── ultralytics diff --git a/ultralytics/cfg/datasets/coco8.yaml b/ultralytics/cfg/datasets/coco8.yaml index eeb5d9dc..97ac4a29 100644 --- a/ultralytics/cfg/datasets/coco8.yaml +++ b/ultralytics/cfg/datasets/coco8.yaml @@ -1,5 +1,6 @@ # Ultralytics YOLO 🚀, AGPL-3.0 license # COCO8 dataset (first 8 images from COCO train2017) by Ultralytics +# Documentation: https://docs.ultralytics.com/datasets/detect/coco8/ # Example usage: yolo train data=coco8.yaml # parent # ├── ultralytics diff --git a/ultralytics/cfg/datasets/open-images-v7.yaml b/ultralytics/cfg/datasets/open-images-v7.yaml index bb1e3ff8..db44dabf 100644 --- a/ultralytics/cfg/datasets/open-images-v7.yaml +++ b/ultralytics/cfg/datasets/open-images-v7.yaml @@ -1,5 +1,6 @@ # Ultralytics YOLO 🚀, AGPL-3.0 license # Open Images v7 dataset https://storage.googleapis.com/openimages/web/index.html by Google +# Documentation: https://docs.ultralytics.com/datasets/detect/open-images-v7/ # Example usage: yolo train data=open-images-v7.yaml # parent # ├── ultralytics diff --git a/ultralytics/cfg/datasets/tiger-pose.yaml b/ultralytics/cfg/datasets/tiger-pose.yaml index 1accef89..2d886c5e 100644 --- a/ultralytics/cfg/datasets/tiger-pose.yaml +++ b/ultralytics/cfg/datasets/tiger-pose.yaml @@ -1,5 +1,6 @@ # Ultralytics YOLO 🚀, AGPL-3.0 license # Tiger Pose dataset by Ultralytics +# Documentation: https://docs.ultralytics.com/datasets/pose/tiger-pose/ # Example usage: yolo train data=tiger-pose.yaml # parent # ├── ultralytics diff --git a/ultralytics/cfg/datasets/xView.yaml b/ultralytics/cfg/datasets/xView.yaml index bdc2d917..6886ceb0 100644 --- a/ultralytics/cfg/datasets/xView.yaml +++ b/ultralytics/cfg/datasets/xView.yaml @@ -1,6 +1,7 @@ # Ultralytics YOLO 🚀, AGPL-3.0 license # DIUx xView 2018 Challenge https://challenge.xviewdataset.org by U.S. National Geospatial-Intelligence Agency (NGA) # -------- DOWNLOAD DATA MANUALLY and jar xf val_images.zip to 'datasets/xView' before running train command! -------- +# Documentation: https://docs.ultralytics.com/datasets/detect/xview/ # Example usage: yolo train data=xView.yaml # parent # ├── ultralytics