Minerva-J / Pytorch-Segmentation-multi-models

Pytorch implementation for Semantic Segmentation with multi models (Deeplabv3, Deeplabv3_plus, PSPNet, UNet, UNet_AutoEncoder, UNet_nested, R2AttUNet, AttentionUNet, RecurrentUNet,, SEGNet, CENet, DsenseASPP, RefineNet, RDFNet)
Apache License 2.0
179 stars 43 forks source link

About dice_loss #5

Open PatrickWilliams44 opened 1 year ago

PatrickWilliams44 commented 1 year ago

Hi Minerva-J! My outputs.shape = [2, 3, 224, 224], targets_x.shape=[2, 224, 224], I want to use dice_loss as the loss function, it requires the input parameter shape to be [B, H, W], how should I modify it? Looking forward to your early reply! Thank you a lot.