PaddleClas v2.0.0

Release Note

Support dynamic graph programming paradigm, adapted to Paddle2.0. Including:

1. 29 series of classification network structures and training configurations, 134 models' pretrained weights and their evaluation metrics.
2. SSLD Knowledge Distillation. Based on this SSLD distillation strategy, the top-1 acc of the distilled model is generally increased by more than 3%.
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.
4. 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%.
5. A variety of training modes, including multi-machine training, mixed precision training, etc.
6. A variety of inference and deployment solutions, including TensorRT inference, Paddle-Lite inference, model service deployment, model quantification, Paddle Hub, etc.
7. Support Linux, Windows, macOS and other systems.
8. Support training/evaluation on CPU/CPU/XPU.