A treasure chest for visual classification and recognition powered by PaddlePaddle
Full Changelog: https://github.com/PaddlePaddle/PaddleClas/compare/v2.5.1...v2.5.2
1.Release PP-ShiTu V2. 2.Release PP-ShiTu V2 android demo. 3.Release PP-ShiTu feature database management tool.
1.Release Practical Ultra Light-weight image Classification solutions. PULC models inference within 3ms on CPU devices, with accuracy on par with SwinTransformer. 2.Release 9 PULC models including person attribute, traffic sign recognition, text image orientation classification, etc. 3.Release PP-HGNet classification network, which is suitable for gpu devices 4.Release PP-LCNet v2 classification network, which is suitable for cpu devices. 5.Add CSwinTransformer, PVTv2, MobileViT and VAN. 6.Add BoT ReID models.
1.Update PP-ShiTu model and add 18MB model series. 2.Upgrade the document completely. 3.Add C++ Inference. 4.Add C++ Pipeline Serving mode. 5.Add a demo for Paddle Lite on Android.
1.Add lite weight models, including detection and feature extraction. 2.Add PP-LCNet backbone model, which is super fast on CPU devices. 3.Support PaddleServing and PaddleSlim. 4.Switch Vector Search module to faiss, due to many compatibility feedback. 5.Add PKSampler, which is more stable on multi-card training. 6.Legendary models now can output middleware result. 7.Add DeepHash module, which can compress float feature to binary feature. 8.SwinTransformer, Twins and Deit achieve same accuracy with the origins training from scratch.
1.Add Swin transformer series model. 2.Support static graph training, support dali and fp16 training. 3.Support build feature gallery with batchsize > 1, support add new feature to existing feature gallery. 4.Fix bugs and update document.
Support dynamic graph programming paradigm, adapted to Paddle2.0. Including: