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.
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.
A treasure chest for visual classification and recognition powered by PaddlePaddle
源项目地址