English | 简体中文

PaddleDetection

The goal of PaddleDetection is to provide easy access to a wide range of object detection models in both industry and research settings. We design PaddleDetection to be not only performant, production-ready but also highly flexible, catering to research needs.

Now all models in PaddleDetection require PaddlePaddle version 1.6 or higher, or suitable develop version.

Introduction

Features:

• Production Ready:

  Key operations are implemented in C++ and CUDA, together with PaddlePaddle's highly efficient inference engine, enables easy deployment in server environments.

• Highly Flexible:

  Components are designed to be modular. Model architectures, as well as data preprocess pipelines, can be easily customized with simple configuration changes.

• Performance Optimized:

  With the help of the underlying PaddlePaddle framework, faster training and reduced GPU memory footprint is achieved. Notably, YOLOv3 training is much faster compared to other frameworks. Another example is Mask-RCNN (ResNet50), we managed to fit up to 4 images per GPU (Tesla V100 16GB) during multi-GPU training.

Supported Architectures:

	ResNet	ResNet-vd 1	ResNeXt-vd	SENet	MobileNet	DarkNet	VGG
Faster R-CNN	✓	✓	x	✓	✗	✗	✗
Faster R-CNN + FPN	✓	✓	✓	✓	✗	✗	✗
Mask R-CNN	✓	✓	x	✓	✗	✗	✗
Mask R-CNN + FPN	✓	✓	✓	✓	✗	✗	✗
Cascade Faster-RCNN	✓	✓	✓	✗	✗	✗	✗
Cascade Mask-RCNN	✓	✗	✗	✓	✗	✗	✗
RetinaNet	✓	✗	✗	✗	✗	✗	✗
YOLOv3	✓	✗	✗	✗	✓	✓	✗
SSD	✗	✗	✗	✗	✓	✗	✓

[1] ResNet-vd models offer much improved accuracy with negligible performance cost.

Advanced Features:

• Synchronized Batch Norm: currently used by YOLOv3.
• Group Norm
• Modulated Deformable Convolution
• Deformable PSRoI Pooling

NOTE: Synchronized batch normalization can only be used on multiple GPU devices, can not be used on CPU devices or single GPU device.

Get Started

• Installation guide
• Quick start on small dataset
• For detailed training and evaluation workflow, please refer to GETTING_STARTED
• Guide to preprocess pipeline and custom dataset
• Introduction to the configuration workflow
• Examples for detailed configuration explanation
• IPython Notebook demo
• Transfer learning document

Model Zoo

• Pretrained models are available in the PaddleDetection model zoo.
• Face detection models
• Pretrained models for pedestrian and vehicle detection

Model compression

• Quantization-aware training example
• Model pruning example

Deployment

• Export model for inference
• C++ inference

Benchmark

• Inference benchmark

Updates

10/2019

• Add enhanced YOLOv3 models, box mAP up to 41.4%.
• Face detection models included: BlazeFace, Faceboxes.
• Enrich COCO models, box mAP up to 51.9%.
• Add CACacascade RCNN, one of the best single model of Objects365 2019 challenge Full Track champion.
• Add pretrained models for pedestrian and vehicle detection.
• Support mixed-precision training.
• Add C++ inference depolyment.
• Add model compression examples.

2/9/2019

• Add retrained models for GroupNorm.

• Add Cascade-Mask-RCNN+FPN.

5/8/2019

• Add a series of models ralated modulated Deformable Convolution.

29/7/2019

• Update Chinese docs for PaddleDetection
• Fix bug in R-CNN models when train and test at the same time
• Add ResNext101-vd + Mask R-CNN + FPN models
• Add YOLOv3 on VOC models

3/7/2019

• Initial release of PaddleDetection and detection model zoo
• Models included: Faster R-CNN, Mask R-CNN, Faster R-CNN+FPN, Mask R-CNN+FPN, Cascade-Faster-RCNN+FPN, RetinaNet, YOLOv3, and SSD.

Contributing

Contributions are highly welcomed and we would really appreciate your feedback!!