search

Tramac / awesome-semantic-segmentation-pytorch

Semantic Segmentation on PyTorch (include FCN, PSPNet, Deeplabv3, Deeplabv3+, DANet, DenseASPP, BiSeNet, EncNet, DUNet, ICNet, ENet, OCNet, CCNet, PSANet, CGNet, ESPNet, LEDNet, DFANet)
Apache License 2.0
2.79k stars 580 forks source link

Why the performance dropped by half when use pytorch1.5 or the newer version? #196

Open bai-shui opened 2 years ago

bai-shui commented 2 years ago

I have trained a model on pytorch1.3. And when I applied the trained model on pytroch1.5 or the newer version to test the same test data, the performance dropped by half. The evaluation indicators used for testing are F1-score and IOU.