简体中文 | English

PaddleClas

Introduction

PaddleClas is a toolset for image classification tasks prepared for the industry and academia. It helps users train better computer vision models and apply them in real scenarios.

Recent update

• 2020.10.12 Add Paddle-Lite demo。
• 2020.10.10 Add cpp inference demo and improve FAQ tutorial.
• 2020.09.17 Add HRNet_W48_C_ssld pretrained model, whose Top-1 Acc on ImageNet-1k dataset reaches 83.62%. Add ResNet34_vd_ssld pretrained model, whose Top-1 Acc on ImageNet-1k dataset reaches 79.72%.
• 2020.09.07 Add HRNet_W18_C_ssld pretrained model, whose Top-1 Acc on ImageNet-1k dataset reaches 81.16%.
• 2020.07.14 Add Res2Net200_vd_26w_4s_ssld pretrained model, whose Top-1 Acc on ImageNet-1k dataset reaches 85.13%. Add Fix_ResNet50_vd_ssld_v2 pretrained model, whose Top-1 Acc on ImageNet-1k dataset reaches 84.00%.
• 2020.06.17 Add English documents.
• 2020.06.12 Add support for training and evaluation on Windows or CPU.
• more

Features

• Rich model zoo. Based on the ImageNet-1k classification dataset, PaddleClas provides 24 series of classification network structures and training configurations, 122 models' pretrained weights and their evaluation metrics.

• SSLD Knowledge Distillation. Based on this SSLD distillation strategy, the top-1 acc of the distilled model is generally increased by more than 3%.

• Data augmentation: PaddleClas provides detailed introduction of 8 data augmentation algorithms such as AutoAugment, Cutout, Cutmix, code reproduction and effect evaluation in a unified experimental environment.

• Pretrained model with 100,000 categories: Based on ResNet50_vd model, Baidu open sourced the ResNet50_vd pretrained model trained on a 100,000-category dataset. In some practical scenarios, the accuracy based on the pretrained weights can be increased by up to 30%.

• A variety of training modes, including multi-machine training, mixed precision training, etc.

• A variety of inference and deployment solutions, including TensorRT inference, Paddle-Lite inference, model service deployment, model quantification, Paddle Hub, etc.

• Support Linux, Windows, macOS and other systems.

Tutorials

• Installation
• Quick start PaddleClas in 30 minutes
• Model introduction and model zoo
  • Model zoo overview
  • ResNet and Vd series
  • Mobile series
  • SEResNeXt and Res2Net series
  • DPN and DenseNet series
  • HRNet series
  • Inception series
  • EfficientNet and ResNeXt101_wsl series
  • ResNeSt and RegNet series
• Model training/evaluation
  • Data preparation
  • Model training and finetuning
  • Model evaluation
• Model prediction/inference
  • Prediction based on training engine
  • Python inference
  • C++ inference
  • Serving deployment
  • Mobile
  • Model Quantization and Compression
• Advanced tutorials
  • Knowledge distillation
  • Data augmentation
• Applications
  • Transfer learning
  • Pretrained model with 100,000 categories
  • Generic object detection
• FAQ
  • General image classification problems
  • PaddleClas FAQ
• Competition support
• License
• Contribution

Model zoo overview

Based on the ImageNet-1k classification dataset, the 24 classification network structures supported by PaddleClas and the corresponding 122 image classification pretrained models are shown below. Training trick, a brief introduction to each series of network structures, and performance evaluation will be shown in the corresponding chapters. The evaluation environment is as follows.

• CPU evaluation environment is based on Snapdragon 855 (SD855).
• The GPU evaluation speed is measured by running 500 times under the FP32+TensorRT configuration (excluding the warmup time of the first 10 times).

Curves of accuracy to the inference time of common server-side models are shown as follows.

Curves of accuracy to the inference time and storage size of common mobile-side models are shown as follows.

ResNet and Vd series

Accuracy and inference time metrics of ResNet and Vd series models are shown as follows. More detailed information can be refered to ResNet and Vd series tutorial.

Mobile series

Accuracy and inference time metrics of Mobile series models are shown as follows. More detailed information can be refered to Mobile series tutorial.

SEResNeXt and Res2Net series

Accuracy and inference time metrics of SEResNeXt and Res2Net series models are shown as follows. More detailed information can be refered to SEResNext and_Res2Net series tutorial.

DPN and DenseNet series

Accuracy and inference time metrics of DPN and DenseNet series models are shown as follows. More detailed information can be refered to DPN and DenseNet series tutorial.

HRNet series

Accuracy and inference time metrics of HRNet series models are shown as follows. More detailed information can be refered to Mobile series tutorial.

Inception series

Accuracy and inference time metrics of Inception series models are shown as follows. More detailed information can be refered to Inception series tutorial.

EfficientNet and ResNeXt101_wsl series

Accuracy and inference time metrics of EfficientNet and ResNeXt101_wsl series models are shown as follows. More detailed information can be refered to EfficientNet and ResNeXt101_wsl series tutorial.

ResNeSt and RegNet series

Accuracy and inference time metrics of ResNeSt and RegNet series models are shown as follows. More detailed information can be refered to ResNeSt and RegNet series tutorial.

License

PaddleClas is released under the 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.