- Release GPU SOTA object detection series models (s/m/l/x) [PP-YOLOE](configs/ppyoloe), achieving mAP as 51.4% on COCO test dataset and 78.1 FPS on Nvidia V100, supporting AMP training and its training speed is 33% faster than PP-YOLOv2.
- Release enhanced models of [PP-PicoDet](configs/picodet), including PP-PicoDet-XS model with 0.7M parameters, its mAP promoted ~2% on COCO, inference speed accelerated 63% on CPU, and post-processing integrated into the network to optimize deployment pipeline.
- Release real-time human analysis tool [PP-Human](deploy/pphuman), which is based on data from real-life situations, supporting pedestrian detection, attribute recognition, human tracking, multi-camera tracking, human statistics and action recognition.
- 2021.11.03: Release [release/2.3](https://github.com/PaddlePaddle/Paddleetection/tree/release/2.3) version. Release mobile object detection model ⚡[PP-PicoDet](configs/picodet), mobile keypoint detection model ⚡[PP-TinyPose](configs/keypoint/tiny_pose)，Real-time tracking system [PP-Tracking](deploy/pptracking). Release object detection models, including [Swin-Transformer](configs/faster_rcnn), [TOOD](configs/tood), [GFL](configs/gfl), release [Sniper](configs/sniper) tiny object detection models and optimized [PP-YOLO-EB](configs/ppyolo) model for EdgeBoard. Release mobile keypoint detection model [Lite HRNet](configs/keypoint).
- 2021.11.03: Release [release/2.3](https://github.com/PaddlePaddle/Paddleetection/tree/release/2.3) version. Release mobile object detection model ⚡[PP-PicoDet](configs/picodet), mobile keypoint detection model ⚡[PP-TinyPose](configs/keypoint/tiny_pose)，Real-time tracking system [PP-Tracking](deploy/pptracking). Release object detection models, including [Swin-Transformer](configs/faster_rcnn), [TOOD](configs/tood), [GFL](configs/gfl), release [Sniper](configs/sniper) tiny object detection models and optimized [PP-YOLO-EB](configs/ppyolo) model for EdgeBoard. Release mobile keypoint detection model [Lite HRNet](configs/keypoint).
- 2021.08.10: Release [release/2.2](https://github.com/PaddlePaddle/Paddleetection/tree/release/2.2) version. Release Transformer object detection models, including [DETR](configs/detr), [Deformable DETR](configs/deformable_detr), [Sparse RCNN](configs/sparse_rcnn). Release [keypoint detection](configs/keypoint) models, including DarkHRNet and model trained on MPII dataset. Release [head-tracking](configs/mot/headtracking21) and [vehicle-tracking](configs/mot/vehicle) multi-object tracking models.
- 2021.08.10: Release [release/2.2](https://github.com/PaddlePaddle/Paddleetection/tree/release/2.2) version. Release Transformer object detection models, including [DETR](configs/detr), [Deformable DETR](configs/deformable_detr), [Sparse RCNN](configs/sparse_rcnn). Release [keypoint detection](configs/keypoint) models, including DarkHRNet and model trained on MPII dataset. Release [head-tracking](configs/mot/headtracking21) and [vehicle-tracking](configs/mot/vehicle) multi-object tracking models.
- 2021.05.20: Release [release/2.1](https://github.com/PaddlePaddle/Paddleetection/tree/release/2.1) version. Release [Keypoint Detection](configs/keypoint), including HigherHRNet and HRNet, [Multi-Object Tracking](configs/mot), including DeepSORT，JDE and FairMOT. Release model compression for PPYOLO series models.Update documents such as [EXPORT ONNX MODEL](deploy/EXPORT_ONNX_MODEL.md).
- 2021.05.20: Release [release/2.1](https://github.com/PaddlePaddle/Paddleetection/tree/release/2.1) version. Release [Keypoint Detection](configs/keypoint), including HigherHRNet and HRNet, [Multi-Object Tracking](configs/mot), including DeepSORT，JDE and FairMOT. Release model compression for PPYOLO series models.Update documents such as [EXPORT ONNX MODEL](deploy/EXPORT_ONNX_MODEL.md).
PaddleDetection is an end-to-end object detection development kit based on PaddlePaddle, which implements varied mainstream object detection, instance segmentation, tracking and keypoint detection algorithms in modular designwhich with configurable modules such as network components, data augmentations and losses, and release many kinds SOTA industry practice models, integrates abilities of model compression and cross-platform high-performance deployment, aims to help developers in the whole end-to-end development in a faster and better way.
PaddleDetection is an end-to-end object detection development kit based on PaddlePaddle, which implements varied mainstream object detection, instance segmentation, tracking and keypoint detection algorithms in modular designwhich with configurable modules such as network components, data augmentations and losses, and release many kinds SOTA industry practice models, integrates abilities of model compression and cross-platform high-performance deployment, aims to help developers in the whole end-to-end development in a faster and better way.
### PaddleDetection provides image processing capabilities such as object detection, instance segmentation, multi-object tracking, keypoint detection and etc.
#### PaddleDetection provides image processing capabilities such as object detection, instance segmentation, multi-object tracking, keypoint detection and etc.
<divalign="center">
<imgsrc="docs/images/ppdet.gif"width="800"/>
</div>
#### PaddleDetection covers industrialization, smart city, security & protection, retail, medicare industry and etc.
## <img src="https://user-images.githubusercontent.com/48054808/157799599-e6a66855-bac6-4e75-b9c0-96e13cb9612f.png" width="20"/> Features
### Features
-**Rich Models**
PaddleDetection provides rich of models, including **250+ pre-trained models** such as **object detection**, **instance segmentation**, **face detection**, **keypoint detection**, **multi-object tracking** and etc, covering a variety of **global competition champion** schemes.
-**Rich Models**
-**Highly Flexible**
PaddleDetection provides rich of models, including **100+ pre-trained models** such as **object detection**, **instance segmentation**, **face detection** etc. It covers a variety of **global competition champion** schemes.
Components are designed to be modular. Model architectures, as well as data preprocess pipelines and optimization strategies, can be easily customized with simple configuration changes.
-**Highly Flexible:**
-**Production Ready**
Components are designed to be modular. Model architectures, as well as data preprocess pipelines and optimization strategies, can be easily customized with simple configuration changes.
From data augmentation, constructing models, training, compression, depolyment, get through end to end, and complete support for multi-architecture, multi-device deployment for **cloud and edge device**.
-**Production Ready:**
-**High Performance**
From data augmentation, constructing models, training, compression, depolyment, get through end to end, and complete support for multi-architecture, multi-device deployment for **cloud and edge device**.
Based on the high performance core of PaddlePaddle, advantages of training speed and memory occupation are obvious. FP16 training and multi-machine training are supported as well.
-**High Performance:**
## <img title="" src="https://user-images.githubusercontent.com/48054808/157800467-2a9946ad-30d1-49a9-b9db-ba33413d9c90.png" alt="" width="20"> Community
Based on the high performance core of PaddlePaddle, advantages of training speed and memory occupation are obvious. FP16 training and multi-machine training are supported as well.
#### Overview of Kit Structures
- If you have any problem or suggestion on PaddleDetection, please send us issues through [GitHub Issues](https://github.com/PaddlePaddle/PaddleDetection/issues).
- Welcome to Join PaddleDetection QQ Group and Wechat Group (reply "Det").
## <img src="https://user-images.githubusercontent.com/48054808/157827140-03ffaff7-7d14-48b4-9440-c38986ea378c.png" width="20"/> Overview of Kit Structures
<tablealign="center">
<tablealign="center">
<tbody>
<tbody>
...
@@ -181,44 +221,43 @@ Based on the high performance core of PaddlePaddle, advantages of training speed
...
@@ -181,44 +221,43 @@ Based on the high performance core of PaddlePaddle, advantages of training speed
</td>
</td>
</tr>
</tr>
</td>
</td>
</tr>
</tr>
</tbody>
</tbody>
</table>
</table>
#### Overview of Model Performance
## <img src="https://user-images.githubusercontent.com/48054808/157801371-9a9a8c65-1690-4123-985a-e0559a7f9494.png" width="20"/> Overview of Model Performance
The relationship between COCO mAP and FPS on Tesla V100 of representative models of each server side architectures and backbones.
The relationship between COCO mAP and FPS on Tesla V100 of representative models of each server side architectures and backbones.
<divalign="center">
<divalign="center">
<imgsrc="docs/images/fps_map.png"/>
<imgsrc="docs/images/fps_map.png"/>
</div>
</div>
**NOTE:**
**NOTE:**
-`CBResNet stands` for `Cascade-Faster-RCNN-CBResNet200vd-FPN`, which has highest mAP on COCO as 53.3%
-`CBResNet stands` for `Cascade-Faster-RCNN-CBResNet200vd-FPN`, which has highest mAP on COCO as 53.3%
-`Cascade-Faster-RCNN` stands for `Cascade-Faster-RCNN-ResNet50vd-DCN`, which has been optimized to 20 FPS inference speed when COCO mAP as 47.8% in PaddleDetection models
-`Cascade-Faster-RCNN` stands for `Cascade-Faster-RCNN-ResNet50vd-DCN`, which has been optimized to 20 FPS inference speed when COCO mAP as 47.8% in PaddleDetection models
-`PP-YOLO` achieves mAP of 45.9% on COCO and 72.9FPS on Tesla V100. Both precision and speed surpass [YOLOv4](https://arxiv.org/abs/2004.10934)
-`PP-YOLO` achieves mAP of 45.9% on COCO and 72.9FPS on Tesla V100. Both precision and speed surpass [YOLOv4](https://arxiv.org/abs/2004.10934)
-`PP-YOLO v2` is optimized version of `PP-YOLO` which has mAP of 49.5% and 68.9FPS on Tesla V100
-`PP-YOLO v2` is optimized version of `PP-YOLO` which has mAP of 49.5% and 68.9FPS on Tesla V100
- All these models can be get in [Model Zoo](#ModelZoo)
- All these models can be get in [Model Zoo](#ModelZoo)
The relationship between COCO mAP and FPS on Qualcomm Snapdragon 865 of representative mobile side models.
The relationship between COCO mAP and FPS on Qualcomm Snapdragon 865 of representative mobile side models.
- All data tested on Qualcomm Snapdragon 865(4\*A77 + 4\*A55) processor with batch size of 1 and CPU threads of 4, and use NCNN library in testing, benchmark scripts is publiced at [MobileDetBenchmark](https://github.com/JiweiMaster/MobileDetBenchmark)
- All data tested on Qualcomm Snapdragon 865(4*A77 + 4*A55) processor with batch size of 1 and CPU threads of 4, and use NCNN library in testing, benchmark scripts is publiced at [MobileDetBenchmark](https://github.com/JiweiMaster/MobileDetBenchmark)
-[PP-PicoDet](configs/picodet) and [PP-YOLO-Tiny](configs/ppyolo) are developed and released by PaddleDetection, other models are not provided in PaddleDetection.
-[PP-PicoDet](configs/picodet) and [PP-YOLO-Tiny](configs/ppyolo) are developed and released by PaddleDetection, other models are not provided in PaddleDetection.
