Can't load model

[HADJHENNI]

Hello, I'm trying to run the code, but each time i try to load the model i get this error : RuntimeError: Error(s) in loading state_dict for ResnetGenerator: Missing key(s) in state_dict: "model.1.bias", "model.4.bias", "model.7.bias", "model.10.conv_block.1.bias", "model.10.conv_block.6.bias", "model.11.conv_block.1.bias", "model.11.conv_block.6.bias", "model.12.conv_block.1.bias", "model.12.conv_block.6.bias", "model.13.conv_block.1.bias", "model.13.conv_block.6.bias", "model.14.conv_block.1.bias", "model.14.conv_block.6.bias", "model.15.conv_block.1.bias", "model.15.conv_block.6.bias", "model.16.conv_block.1.bias", "model.16.conv_block.6.bias", "model.17.conv_block.1.bias", "model.17.conv_block.6.bias", "model.18.conv_block.1.bias", "model.18.conv_block.6.bias", "model.19.bias", "model.22.bias". .....

any suggestions to solve this issue ? Thank you

[mtli]

Hi, if you are using compatible model definition and checkpoint, then the cause is most likely the inconsistency with the saving and loading of nn.DataParellel and/or weight devices, for which you can check out this post.

[mychina75]

@HADJHENNI Have you solved the issue? met with the same issue... @mtli Did you train the model using 3 GPU cards?