English | 简体中文
PaddleDetection is an end-to-end object detection development kit based on PaddlePaddle, which aims to help developers in the whole development of constructing, training, optimizing and deploying detection models in a faster and better way.
PaddleDetection implements varied mainstream object detection algorithms in modular design, and provides wealthy data augmentation methods, network components(such as backbones), loss functions, etc., and integrates abilities of model compression and cross-platform high-performance deployment.
After a long time of industry practice polishing, PaddleDetection has had smooth and excellent user experience, it has been widely used by developers in more than ten industries such as industrial quality inspection, remote sensing image object detection, automatic inspection, new retail, Internet, and scientific research.
release/0.5version, Please refer to change log for details.
Rich Models 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.
Use Concisely Modular design, decouple each network component, developers easily build and try various detection models and optimization strategies, quickly get high-performance, customized algorithm.
Getting Through End to End 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.
High Performance: Based on the high performance core of PaddlePaddle, advantages of training speed and memory occupation are obvious. Support FP16 training, support multi-machine training.
The relationship between COCO mAP and FPS on Tesla V100 of representative models of each architectures and backbones.
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
The enhanced PaddleDetection model
YOLOv3-ResNet50vd-DCN is 10.6 absolute percentage points higher than paper on COCO mAP, and inference speed is 61.3 fps, nearly 70% faster than the darknet framework.
All these models can be get in Model Zoo
Model Compression(Based on PaddleSlim)
Inference and deployment
v0.5.0 was released at
11/2020, add SOLOv2, etc. And add Android mobile demo, add PACT quantization strategy, add object detection full-process documentation and Jetson platform deployment tutorials, and improved ease of use, fix many known bugs, etc. Please refer to change log for details.
PaddleDetection is released under the Apache 2.0 license.
Contributions are highly welcomed and we would really appreciate your feedback!!
：Code submit frequency
：React/respond to issue & PR etc.
：Well-balanced team members and collaboration
：Recent popularity of project
：Star counts, download counts etc.