简体中文 | English

PaddleClas

Introduction

PaddleClas is an image recognition toolset for industry and academia, helping users train better computer vision models and apply them in real scenarios.

Recent updates

• 2022.4.21 Added the related code of the CVPR2022 oral paper MixFormer.

• 2021.09.17 Add PP-LCNet series model developed by PaddleClas, these models show strong competitiveness on Intel CPUs. For the introduction of PP-LCNet, please refer to paper or PP-LCNet model introduction. The metrics and pretrained model are available here.

• 2021.06.29 Add Swin-transformer series model，Highest top1 acc on ImageNet1k dataset reaches 87.2%, training, evaluation and inference are all supported. Pretrained models can be downloaded here.

• 2021.06.16 PaddleClas release/2.2. Add metric learning and vector search modules. Add product recognition, animation character recognition, vehicle recognition and logo recognition. Added 30 pretrained models of LeViT, Twins, TNT, DLA, HarDNet, and RedNet, and the accuracy is roughly the same as that of the paper.

• more

Features

• A practical image recognition system consist of detection, feature learning and retrieval modules, widely applicable to all types of image recognition tasks. Four sample solutions are provided, including product recognition, vehicle recognition, logo recognition and animation character recognition.

• Rich library of pre-trained models: Provide a total of 164 ImageNet pre-trained models in 35 series, among which 6 selected series of models support fast structural modification.

• Comprehensive and easy-to-use feature learning components: 12 metric learning methods are integrated and can be combined and switched at will through configuration files.

• SSLD knowledge distillation: The 14 classification pre-training models generally improved their accuracy by more than 3%; among them, the ResNet50_vd model achieved a Top-1 accuracy of 84.0% on the Image-Net-1k dataset and the Res2Net200_vd pre-training model achieved a Top-1 accuracy of 85.1%.

• Data augmentation: Provide 8 data augmentation algorithms such as AutoAugment, Cutout, Cutmix, etc. with detailed introduction, code replication and evaluation of effectiveness in a unified experimental environment.

Welcome to Join the Technical Exchange Group

• You can also scan the QR code below to join the PaddleClas QQ group and WeChat group (add and replay "C") to get more efficient answers to your questions and to communicate with developers from all walks of life. We look forward to hearing from you.

Quick Start

Quick experience of image recognition：Link

Tutorials

• Quick Installation
• Quick Start of Recognition
• Introduction to Image Recognition Systems
• Demo images
• Algorithms Introduction
  • Backbone Network and Pre-trained Model Library
  • Mainbody Detection
  • Image Classification
  • Feature Learning
    • Product Recognition
    • Vehicle Recognition
    • Logo Recognition
    • Animation Character Recognition
  • Vector Search
• Models Training/Evaluation
  • Image Classification
  • Feature Learning
• Inference Model Prediction
  • Python Inference
  • C++ Classfication Inference， C++ PP-ShiTu Inference
• Model Deploy (only support classification for now, recognition coming soon)
  • Hub Serving Deployment
  • Mobile Deployment
  • Inference Using whl
• Advanced Tutorial
  • Knowledge Distillation
  • Model Quantization
  • Data Augmentation
• License
• Contribution

Introduction to Image Recognition Systems

Image recognition can be divided into three steps:

• （1）Identify region proposal for target objects through a detection model；
• （2）Extract features for each region proposal;
• （3）Search features in the retrieval database and output results;

For a new unknown category, there is no need to retrain the model, just prepare images of new category, extract features and update retrieval database and the category can be recognised.

Demo images more

• Product recognition

• Cartoon character recognition

• Logo recognition

• Car recognition

License

PaddleClas is released under the Apache 2.0 license Apache 2.0 license

Contribution

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

• Thank nblib to fix bug of RandErasing.
• Thank chenpy228 to fix some typos PaddleClas.
• Thank jm12138 to add ViT, DeiT models and RepVGG models into PaddleClas.
• Thank FutureSI to parse and summarize the PaddleClas code.