Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Loading State Dict #4

Closed
vatsalag99 opened this issue Sep 15, 2019 · 10 comments
Closed

Loading State Dict #4

vatsalag99 opened this issue Sep 15, 2019 · 10 comments

Comments

@vatsalag99
Copy link

Hello, I am trying to load in the state dict provided in the OneDrive link, but ran into issues due to there being differences between the expected state_dict and the given one. Specifically, the res2net101 checkpoint is failing for me.
@gasvn
Copy link
Member

gasvn commented Sep 16, 2019

Can you please show me what the exact error is? Maybe it's easier for me to find the problem.

@vatsalag99
Copy link
Author

vatsalag99 commented Sep 16, 2019 •
edited

Hi, the error is as follows:

RuntimeError: Error(s) in loading state_dict for Res2Net:
Missing key(s) in state_dict: "layer1.0.convs.0.weight", "layer1.0.convs.1.weight", "layer1.0.convs.2.weight", "layer1.0.bns.0.weight", "layer1.0.bns.0.bias", "layer1.0.bns.0.running_mean", "layer1.0.bns.0.running_var", "layer1.0.bns.1.weight", "layer1.0.bns.1.bias", "layer1.0.bns.1.running_mean", "layer1.0.bns.1.running_var", "layer1.0.bns.2.weight", "layer1.0.bns.2.bias", "layer1.0.bns.2.running_mean", "layer1.0.bns.2.running_var", "layer1.1.convs.0.weight", "layer1.1.convs.1.weight", "layer1.1.convs.2.weight", "layer1.1.bns.0.weight", "layer1.1.bns.0.bias", "layer1.1.bns.0.running_mean", "layer1.1.bns.0.running_var", "layer1.1.bns.1.weight", "layer1.1.bns.1.bias", "layer1.1.bns.1.running_mean", "layer1.1.bns.1.running_var", "layer1.1.bns.2.weight", "layer1.1.bns.2.bias", "layer1.1.bns.2.running_mean", "layer1.1.bns.2.running_var", "layer1.2.convs.0.weight", "layer1.2.convs.1.weight", "layer1.2.convs.2.weight", "layer1.2.bns.0.weight", "layer1.2.bns.0.bias", "layer1.2.bns.0.running_mean", "layer1.2.bns.0.running_var", "layer1.2.bns.1.weight", "layer1.2.bns.1.bias", "layer1.2.bns.1.running_mean", "layer1.2.bns.1.running_var", "layer1.2.bns.2.weight", "layer1.2.bns.2.bias", "layer1.2.bns.2.running_mean", "layer1.2.bns.2.running_var", "layer2.0.convs.0.weight", "layer2.0.convs.1.weight", "layer2.0.convs.2.weight", "layer2.0.bns.0.weight", "layer2.0.bns.0.bias", "layer2.0.bns.0.running_mean", "layer2.0.bns.0.running_var", "layer2.0.bns.1.weight", "layer2.0.bns.1.bias", "layer2.0.bns.1.running_mean", "layer2.0.bns.1.running_var", "layer2.0.bns.2.weight", "layer2.0.bns.2.bias", "layer2.0.bns.2.running_mean", "layer2.0.bns.2.running_var", "layer2.1.convs.0.weight", "layer2.1.convs.1.weight", "layer2.1.convs.2.weight", "layer2.1.bns.0.weight", "layer2.1.bns.0.bias", "layer2.1.bns.0.running_mean", "layer2.1.bns.0.running_var", "layer2.1.bns.1.weight", "layer2.1.bns.1.bias", "layer2.1.bns.1.running_mean", "layer2.1.bns.1.running_var", "layer2.1.bns.2.weight", "layer2.1.bns.2.bias", "layer2.1.bns.2.running_mean", "layer2.1.bns.2.running_var", "layer2.2.convs.0.weight", "layer2.2.convs.1.weight", "layer2.2.convs.2.weight", "layer2.2.bns.0.weight", "layer2.2.bns.0.bias", "layer2.2.bns.0.running_mean", "layer2.2.bns.0.running_var", "layer2.2.bns.1.weight", "layer2.2.bns.1.bias", "layer2.2.bns.1.running_mean", "layer2.2.bns.1.running_var", "layer2.2.bns.2.weight", "layer2.2.bns.2.bias", "layer2.2.bns.2.running_mean", "layer2.2.bns.2.running_var", "layer2.3.convs.0.weight", "layer2.3.convs.1.weight", "layer2.3.convs.2.weight", "layer2.3.bns.0.weight", "layer2.3.bns.0.bias", "layer2.3.bns.0.running_mean", "layer2.3.bns.0.running_var", "layer2.3.bns.1.weight", "layer2.3.bns.1.bias", "layer2.3.bns.1.running_mean", "layer2.3.bns.1.running_var", "layer2.3.bns.2.weight", "layer2.3.bns.2.bias", "layer2.3.bns.2.running_mean", "layer2.3.bns.2.running_var", "layer3.0.convs.0.weight", "layer3.0.convs.1.weight", "layer3.0.convs.2.weight", "layer3.0.bns.0.weight", "layer3.0.bns.0.bias", "layer3.0.bns.0.running_mean", "layer3.0.bns.0.running_var", "layer3.0.bns.1.weight", "layer3.0.bns.1.bias", "layer3.0.bns.1.running_mean", "layer3.0.bns.1.running_var", "layer3.0.bns.2.weight", "layer3.0.bns.2.bias", "layer3.0.bns.2.running_mean", "layer3.0.bns.2.running_var", "layer3.1.convs.0.weight", "layer3.1.convs.1.weight", "layer3.1.convs.2.weight", "layer3.1.bns.0.weight", "layer3.1.bns.0.bias", "layer3.1.bns.0.running_mean", "layer3.1.bns.0.running_var", "layer3.1.bns.1.weight", "layer3.1.bns.1.bias", "layer3.1.bns.1.running_mean", "layer3.1.bns.1.running_var", "layer3.1.bns.2.weight", "layer3.1.bns.2.bias", "layer3.1.bns.2.running_mean", "layer3.1.bns.2.running_var", "layer3.2.convs.0.weight", "layer3.2.convs.1.weight", "layer3.2.convs.2.weight", "layer3.2.bns.0.weight", "layer3.2.bns.0.bias", "layer3.2.bns.0.running_mean", "layer3.2.bns.0.running_var", "layer3.2.bns.1.weight", "layer3.2.bns.1.bias", "layer3.2.bns.1.running_mean", "layer3.2.bns.1.running_var", "layer3.2.bns.2.weight", "layer3.2.bns.2.bias", "layer3.2.bns.2.running_mean", "layer3.2.bns.2.running_var", "layer3.3.convs.0.weight", "layer3.3.convs.1.weight", "layer3.3.convs.2.weight", "layer3.3.bns.0.weight", "layer3.3.bns.0.bias", "layer3.3.bns.0.running_mean", "layer3.3.bns.0.running_var", "layer3.3.bns.1.weight", "layer3.3.bns.1.bias", "layer3.3.bns.1.running_mean", "layer3.3.bns.1.running_var", "layer3.3.bns.2.weight", "layer3.3.bns.2.bias", "layer3.3.bns.2.running_mean", "layer3.3.bns.2.running_var", "layer3.4.convs.0.weight", "layer3.4.convs.1.weight", "layer3.4.convs.2.weight", "layer3.4.bns.0.weight", "layer3.4.bns.0.bias", "layer3.4.bns.0.running_mean", "layer3.4.bns.0.running_var", "layer3.4.bns.1.weight", "layer3.4.bns.1.bias", "layer3.4.bns.1.running_mean", "layer3.4.bns.1.running_var", "layer3.4.bns.2.weight", "layer3.4.bns.2.bias", "layer3.4.bns.2.running_mean", "layer3.4.bns.2.running_var", "layer3.5.convs.0.weight", "layer3.5.convs.1.weight", "layer3.5.convs.2.weight", "layer3.5.bns.0.weight", "layer3.5.bns.0.bias", "layer3.5.bns.0.running_mean", "layer3.5.bns.0.running_var", "layer3.5.bns.1.weight", "layer3.5.bns.1.bias", "layer3.5.bns.1.running_mean", "layer3.5.bns.1.running_var", "layer3.5.bns.2.weight", "layer3.5.bns.2.bias", "layer3.5.bns.2.running_mean", "layer3.5.bns.2.running_var", "layer3.6.convs.0.weight", "layer3.6.convs.1.weight", "layer3.6.convs.2.weight", "layer3.6.bns.0.weight", "layer3.6.bns.0.bias", "layer3.6.bns.0.running_mean", "layer3.6.bns.0.running_var", "layer3.6.bns.1.weight", "layer3.6.bns.1.bias", "layer3.6.bns.1.running_mean", "layer3.6.bns.1.running_var", "layer3.6.bns.2.weight", "layer3.6.bns.2.bias", "layer3.6.bns.2.running_mean", "layer3.6.bns.2.running_var", "layer3.7.convs.0.weight", "layer3.7.convs.1.weight", "layer3.7.convs.2.weight", "layer3.7.bns.0.weight", "layer3.7.bns.0.bias", "layer3.7.bns.0.running_mean", "layer3.7.bns.0.running_var", "layer3.7.bns.1.weight", "layer3.7.bns.1.bias", "layer3.7.bns.1.running_mean", "layer3.7.bns.1.running_var", "layer3.7.bns.2.weight", "layer3.7.bns.2.bias", "layer3.7.bns.2.running_mean", "layer3.7.bns.2.running_var", "layer3.8.convs.0.weight", "layer3.8.convs.1.weight", "layer3.8.convs.2.weight", "layer3.8.bns.0.weight", "layer3.8.bns.0.bias", "layer3.8.bns.0.running_mean", "layer3.8.bns.0.running_var", "layer3.8.bns.1.weight", "layer3.8.bns.1.bias", "layer3.8.bns.1.running_mean", "layer3.8.bns.1.running_var", "layer3.8.bns.2.weight", "layer3.8.bns.2.bias", "layer3.8.bns.2.running_mean", "layer3.8.bns.2.running_var", "layer3.9.convs.0.weight", "layer3.9.convs.1.weight", "layer3.9.convs.2.weight", "layer3.9.bns.0.weight", "layer3.9.bns.0.bias", "layer3.9.bns.0.running_mean", "layer3.9.bns.0.running_var", "layer3.9.bns.1.weight", "layer3.9.bns.1.bias", "layer3.9.bns.1.running_mean", "layer3.9.bns.1.running_var", "layer3.9.bns.2.weight", "layer3.9.bns.2.bias", "layer3.9.bns.2.running_mean", "layer3.9.bns.2.running_var", "layer3.10.convs.0.weight", "layer3.10.convs.1.weight", "layer3.10.convs.2.weight", "layer3.10.bns.0.weight", "layer3.10.bns.0.bias", "layer3.10.bns.0.running_mean", "layer3.10.bns.0.running_var", "layer3.10.bns.1.weight", "layer3.10.bns.1.bias", "layer3.10.bns.1.running_mean", "layer3.10.bns.1.running_var", "layer3.10.bns.2.weight", "layer3.10.bns.2.bias", "layer3.10.bns.2.running_mean", "layer3.10.bns.2.running_var", "layer3.11.convs.0.weight", "layer3.11.convs.1.weight", "layer3.11.convs.2.weight", "layer3.11.bns.0.weight", "layer3.11.bns.0.bias", "layer3.11.bns.0.running_mean", "layer3.11.bns.0.running_var", "layer3.11.bns.1.weight", "layer3.11.bns.1.bias", "layer3.11.bns.1.running_mean", "layer3.11.bns.1.running_var", "layer3.11.bns.2.weight", "layer3.11.bns.2.bias", "layer3.11.bns.2.running_mean", "layer3.11.bns.2.running_var", "layer3.12.convs.0.weight", "layer3.12.convs.1.weight", "layer3.12.convs.2.weight", "layer3.12.bns.0.weight", "layer3.12.bns.0.bias", "layer3.12.bns.0.running_mean", "layer3.12.bns.0.running_var", "layer3.12.bns.1.weight", "layer3.12.bns.1.bias", "layer3.12.bns.1.running_mean", "layer3.12.bns.1.running_var", "layer3.12.bns.2.weight", "layer3.12.bns.2.bias", "layer3.12.bns.2.running_mean", "layer3.12.bns.2.running_var", "layer3.13.convs.0.weight", "layer3.13.convs.1.weight", "layer3.13.convs.2.weight", "layer3.13.bns.0.weight", "layer3.13.bns.0.bias", "layer3.13.bns.0.running_mean", "layer3.13.bns.0.running_var", "layer3.13.bns.1.weight", "layer3.13.bns.1.bias", "layer3.13.bns.1.running_mean", "layer3.13.bns.1.running_var", "layer3.13.bns.2.weight", "layer3.13.bns.2.bias", "layer3.13.bns.2.running_mean", "layer3.13.bns.2.running_var", "layer3.14.convs.0.weight", "layer3.14.convs.1.weight", "layer3.14.convs.2.weight", "layer3.14.bns.0.weight", "layer3.14.bns.0.bias", "layer3.14.bns.0.running_mean", "layer3.14.bns.0.running_var", "layer3.14.bns.1.weight", "layer3.14.bns.1.bias", "layer3.14.bns.1.running_mean", "layer3.14.bns.1.running_var", "layer3.14.bns.2.weight", "layer3.14.bns.2.bias", "layer3.14.bns.2.running_mean", "layer3.14.bns.2.running_var", "layer3.15.convs.0.weight", "layer3.15.convs.1.weight", "layer3.15.convs.2.weight", "layer3.15.bns.0.weight", "layer3.15.bns.0.bias", "layer3.15.bns.0.running_mean", "layer3.15.bns.0.running_var", "layer3.15.bns.1.weight", "layer3.15.bns.1.bias", "layer3.15.bns.1.running_mean", "layer3.15.bns.1.running_var", "layer3.15.bns.2.weight", "layer3.15.bns.2.bias", "layer3.15.bns.2.running_mean", "layer3.15.bns.2.running_var", "layer3.16.convs.0.weight", "layer3.16.convs.1.weight", "layer3.16.convs.2.weight", "layer3.16.bns.0.weight", "layer3.16.bns.0.bias", "layer3.16.bns.0.running_mean", "layer3.16.bns.0.running_var", "layer3.16.bns.1.weight", "layer3.16.bns.1.bias", "layer3.16.bns.1.running_mean", "layer3.16.bns.1.running_var", "layer3.16.bns.2.weight", "layer3.16.bns.2.bias", "layer3.16.bns.2.running_mean", "layer3.16.bns.2.running_var", "layer3.17.convs.0.weight", "layer3.17.convs.1.weight", "layer3.17.convs.2.weight", "layer3.17.bns.0.weight", "layer3.17.bns.0.bias", "layer3.17.bns.0.running_mean", "layer3.17.bns.0.running_var", "layer3.17.bns.1.weight", "layer3.17.bns.1.bias", "layer3.17.bns.1.running_mean", "layer3.17.bns.1.running_var", "layer3.17.bns.2.weight", "layer3.17.bns.2.bias", "layer3.17.bns.2.running_mean", "layer3.17.bns.2.running_var", "layer3.18.convs.0.weight", "layer3.18.convs.1.weight", "layer3.18.convs.2.weight", "layer3.18.bns.0.weight", "layer3.18.bns.0.bias", "layer3.18.bns.0.running_mean", "layer3.18.bns.0.running_var", "layer3.18.bns.1.weight", "layer3.18.bns.1.bias", "layer3.18.bns.1.running_mean", "layer3.18.bns.1.running_var", "layer3.18.bns.2.weight", "layer3.18.bns.2.bias", "layer3.18.bns.2.running_mean", "layer3.18.bns.2.running_var", "layer3.19.convs.0.weight", "layer3.19.convs.1.weight", "layer3.19.convs.2.weight", "layer3.19.bns.0.weight", "layer3.19.bns.0.bias", "layer3.19.bns.0.running_mean", "layer3.19.bns.0.running_var", "layer3.19.bns.1.weight", "layer3.19.bns.1.bias", "layer3.19.bns.1.running_mean", "layer3.19.bns.1.running_var", "layer3.19.bns.2.weight", "layer3.19.bns.2.bias", "layer3.19.bns.2.running_mean", "layer3.19.bns.2.running_var", "layer3.20.convs.0.weight", "layer3.20.convs.1.weight", "layer3.20.convs.2.weight", "layer3.20.bns.0.weight", "layer3.20.bns.0.bias", "layer3.20.bns.0.running_mean", "layer3.20.bns.0.running_var", "layer3.20.bns.1.weight", "layer3.20.bns.1.bias", "layer3.20.bns.1.running_mean", "layer3.20.bns.1.running_var", "layer3.20.bns.2.weight", "layer3.20.bns.2.bias", "layer3.20.bns.2.running_mean", "layer3.20.bns.2.running_var", "layer3.21.convs.0.weight", "layer3.21.convs.1.weight", "layer3.21.convs.2.weight", "layer3.21.bns.0.weight", "layer3.21.bns.0.bias", "layer3.21.bns.0.running_mean", "layer3.21.bns.0.running_var", "layer3.21.bns.1.weight", "layer3.21.bns.1.bias", "layer3.21.bns.1.running_mean", "layer3.21.bns.1.running_var", "layer3.21.bns.2.weight", "layer3.21.bns.2.bias", "layer3.21.bns.2.running_mean", "layer3.21.bns.2.running_var", "layer3.22.convs.0.weight", "layer3.22.convs.1.weight", "layer3.22.convs.2.weight", "layer3.22.bns.0.weight", "layer3.22.bns.0.bias", "layer3.22.bns.0.running_mean", "layer3.22.bns.0.running_var", "layer3.22.bns.1.weight", "layer3.22.bns.1.bias", "layer3.22.bns.1.running_mean", "layer3.22.bns.1.running_var", "layer3.22.bns.2.weight", "layer3.22.bns.2.bias", "layer3.22.bns.2.running_mean", "layer3.22.bns.2.running_var", "layer4.0.convs.0.weight", "layer4.0.convs.1.weight", "layer4.0.convs.2.weight", "layer4.0.bns.0.weight", "layer4.0.bns.0.bias", "layer4.0.bns.0.running_mean", "layer4.0.bns.0.running_var", "layer4.0.bns.1.weight", "layer4.0.bns.1.bias", "layer4.0.bns.1.running_mean", "layer4.0.bns.1.running_var", "layer4.0.bns.2.weight", "layer4.0.bns.2.bias", "layer4.0.bns.2.running_mean", "layer4.0.bns.2.running_var", "layer4.1.convs.0.weight", "layer4.1.convs.1.weight", "layer4.1.convs.2.weight", "layer4.1.bns.0.weight", "layer4.1.bns.0.bias", "layer4.1.bns.0.running_mean", "layer4.1.bns.0.running_var", "layer4.1.bns.1.weight", "layer4.1.bns.1.bias", "layer4.1.bns.1.running_mean", "layer4.1.bns.1.running_var", "layer4.1.bns.2.weight", "layer4.1.bns.2.bias", "layer4.1.bns.2.running_mean", "layer4.1.bns.2.running_var", "layer4.2.convs.0.weight", "layer4.2.convs.1.weight", "layer4.2.convs.2.weight", "layer4.2.bns.0.weight", "layer4.2.bns.0.bias", "layer4.2.bns.0.running_mean", "layer4.2.bns.0.running_var", "layer4.2.bns.1.weight", "layer4.2.bns.1.bias", "layer4.2.bns.1.running_mean", "layer4.2.bns.1.running_var", "layer4.2.bns.2.weight", "layer4.2.bns.2.bias", "layer4.2.bns.2.running_mean", "layer4.2.bns.2.running_var".
Unexpected key(s) in state_dict: "layer1.0.conv2.weight", "layer1.0.bn2.running_mean", "layer1.0.bn2.running_var", "layer1.0.bn2.weight", "layer1.0.bn2.bias", "layer1.1.conv2.weight", "layer1.1.bn2.running_mean", "layer1.1.bn2.running_var", "layer1.1.bn2.weight", "layer1.1.bn2.bias", "layer1.2.conv2.weight", "layer1.2.bn2.running_mean", "layer1.2.bn2.running_var", "layer1.2.bn2.weight", "layer1.2.bn2.bias", "layer2.0.conv2.weight", "layer2.0.bn2.running_mean", "layer2.0.bn2.running_var", "layer2.0.bn2.weight", "layer2.0.bn2.bias", "layer2.1.conv2.weight", "layer2.1.bn2.running_mean", "layer2.1.bn2.running_var", "layer2.1.bn2.weight", "layer2.1.bn2.bias", "layer2.2.conv2.weight", "layer2.2.bn2.running_mean", "layer2.2.bn2.running_var", "layer2.2.bn2.weight", "layer2.2.bn2.bias", "layer2.3.conv2.weight", "layer2.3.bn2.running_mean", "layer2.3.bn2.running_var", "layer2.3.bn2.weight", "layer2.3.bn2.bias", "layer3.0.conv2.weight", "layer3.0.bn2.running_mean", "layer3.0.bn2.running_var", "layer3.0.bn2.weight", "layer3.0.bn2.bias", "layer3.1.conv2.weight", "layer3.1.bn2.running_mean", "layer3.1.bn2.running_var", "layer3.1.bn2.weight", "layer3.1.bn2.bias", "layer3.2.conv2.weight", "layer3.2.bn2.running_mean", "layer3.2.bn2.running_var", "layer3.2.bn2.weight", "layer3.2.bn2.bias", "layer3.3.conv2.weight", "layer3.3.bn2.running_mean", "layer3.3.bn2.running_var", "layer3.3.bn2.weight", "layer3.3.bn2.bias", "layer3.4.conv2.weight", "layer3.4.bn2.running_mean", "layer3.4.bn2.running_var", "layer3.4.bn2.weight", "layer3.4.bn2.bias", "layer3.5.conv2.weight", "layer3.5.bn2.running_mean", "layer3.5.bn2.running_var", "layer3.5.bn2.weight", "layer3.5.bn2.bias", "layer3.6.conv2.weight", "layer3.6.bn2.running_mean", "layer3.6.bn2.running_var", "layer3.6.bn2.weight", "layer3.6.bn2.bias", "layer3.7.conv2.weight", "layer3.7.bn2.running_mean", "layer3.7.bn2.running_var", "layer3.7.bn2.weight", "layer3.7.bn2.bias", "layer3.8.conv2.weight", "layer3.8.bn2.running_mean", "layer3.8.bn2.running_var", "layer3.8.bn2.weight", "layer3.8.bn2.bias", "layer3.9.conv2.weight", "layer3.9.bn2.running_mean", "layer3.9.bn2.running_var", "layer3.9.bn2.weight", "layer3.9.bn2.bias", "layer3.10.conv2.weight", "layer3.10.bn2.running_mean", "layer3.10.bn2.running_var", "layer3.10.bn2.weight", "layer3.10.bn2.bias", "layer3.11.conv2.weight", "layer3.11.bn2.running_mean", "layer3.11.bn2.running_var", "layer3.11.bn2.weight", "layer3.11.bn2.bias", "layer3.12.conv2.weight", "layer3.12.bn2.running_mean", "layer3.12.bn2.running_var", "layer3.12.bn2.weight", "layer3.12.bn2.bias", "layer3.13.conv2.weight", "layer3.13.bn2.running_mean", "layer3.13.bn2.running_var", "layer3.13.bn2.weight", "layer3.13.bn2.bias", "layer3.14.conv2.weight", "layer3.14.bn2.running_mean", "layer3.14.bn2.running_var", "layer3.14.bn2.weight", "layer3.14.bn2.bias", "layer3.15.conv2.weight", "layer3.15.bn2.running_mean", "layer3.15.bn2.running_var", "layer3.15.bn2.weight", "layer3.15.bn2.bias", "layer3.16.conv2.weight", "layer3.16.bn2.running_mean", "layer3.16.bn2.running_var", "layer3.16.bn2.weight", "layer3.16.bn2.bias", "layer3.17.conv2.weight", "layer3.17.bn2.running_mean", "layer3.17.bn2.running_var", "layer3.17.bn2.weight", "layer3.17.bn2.bias", "layer3.18.conv2.weight", "layer3.18.bn2.running_mean", "layer3.18.bn2.running_var", "layer3.18.bn2.weight", "layer3.18.bn2.bias", "layer3.19.conv2.weight", "layer3.19.bn2.running_mean", "layer3.19.bn2.running_var", "layer3.19.bn2.weight", "layer3.19.bn2.bias", "layer3.20.conv2.weight", "layer3.20.bn2.running_mean", "layer3.20.bn2.running_var", "layer3.20.bn2.weight", "layer3.20.bn2.bias", "layer3.21.conv2.weight", "layer3.21.bn2.running_mean", "layer3.21.bn2.running_var", "layer3.21.bn2.weight", "layer3.21.bn2.bias", "layer3.22.conv2.weight", "layer3.22.bn2.running_mean", "layer3.22.bn2.running_var", "layer3.22.bn2.weight", "layer3.22.bn2.bias", "layer4.0.conv2.weight", "layer4.0.bn2.running_mean", "layer4.0.bn2.running_var", "layer4.0.bn2.weight", "layer4.0.bn2.bias", "layer4.1.conv2.weight", "layer4.1.bn2.running_mean", "layer4.1.bn2.running_var", "layer4.1.bn2.weight", "layer4.1.bn2.bias", "layer4.2.conv2.weight", "layer4.2.bn2.running_mean", "layer4.2.bn2.running_var", "layer4.2.bn2.weight", "layer4.2.bn2.bias".
size mismatch for layer1.0.conv1.weight: copying a param with shape torch.Size([64, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([104, 64, 1, 1]).
size mismatch for layer1.0.bn1.weight: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([104]).
size mismatch for layer1.0.bn1.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([104]).
size mismatch for layer1.0.bn1.running_mean: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([104]).
size mismatch for layer1.0.bn1.running_var: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([104]).
size mismatch for layer1.0.conv3.weight: copying a param with shape torch.Size([256, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 104, 1, 1]).
size mismatch for layer1.1.conv1.weight: copying a param with shape torch.Size([64, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([104, 256, 1, 1]).
size mismatch for layer1.1.bn1.weight: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([104]).
size mismatch for layer1.1.bn1.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([104]).
size mismatch for layer1.1.bn1.running_mean: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([104]).
size mismatch for layer1.1.bn1.running_var: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([104]).
size mismatch for layer1.1.conv3.weight: copying a param with shape torch.Size([256, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 104, 1, 1]).
size mismatch for layer1.2.conv1.weight: copying a param with shape torch.Size([64, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([104, 256, 1, 1]).
size mismatch for layer1.2.bn1.weight: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([104]).
size mismatch for layer1.2.bn1.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([104]).
size mismatch for layer1.2.bn1.running_mean: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([104]).
size mismatch for layer1.2.bn1.running_var: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([104]).
size mismatch for layer1.2.conv3.weight: copying a param with shape torch.Size([256, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 104, 1, 1]).
size mismatch for layer2.0.conv1.weight: copying a param with shape torch.Size([128, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([208, 256, 1, 1]).
size mismatch for layer2.0.bn1.weight: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.0.bn1.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.0.bn1.running_mean: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.0.bn1.running_var: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.0.conv3.weight: copying a param with shape torch.Size([512, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([512, 208, 1, 1]).
size mismatch for layer2.1.conv1.weight: copying a param with shape torch.Size([128, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([208, 512, 1, 1]).
size mismatch for layer2.1.bn1.weight: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.1.bn1.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.1.bn1.running_mean: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.1.bn1.running_var: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.1.conv3.weight: copying a param with shape torch.Size([512, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([512, 208, 1, 1]).
size mismatch for layer2.2.conv1.weight: copying a param with shape torch.Size([128, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([208, 512, 1, 1]).
size mismatch for layer2.2.bn1.weight: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.2.bn1.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.2.bn1.running_mean: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.2.bn1.running_var: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.2.conv3.weight: copying a param with shape torch.Size([512, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([512, 208, 1, 1]).
size mismatch for layer2.3.conv1.weight: copying a param with shape torch.Size([128, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([208, 512, 1, 1]).
size mismatch for layer2.3.bn1.weight: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.3.bn1.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.3.bn1.running_mean: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.3.bn1.running_var: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.3.conv3.weight: copying a param with shape torch.Size([512, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([512, 208, 1, 1]).
size mismatch for layer3.0.conv1.weight: copying a param with shape torch.Size([256, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 512, 1, 1]).
size mismatch for layer3.0.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.0.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.0.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.0.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.0.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.1.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.1.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.1.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.1.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.1.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.1.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.2.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.2.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.2.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.2.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.2.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.2.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.3.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.3.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.3.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.3.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.3.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.3.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.4.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.4.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.4.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.4.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.4.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.4.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.5.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.5.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.5.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.5.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.5.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.5.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.6.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.6.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.6.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.6.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.6.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.6.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.7.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.7.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.7.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.7.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.7.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.7.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.8.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.8.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.8.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.8.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.8.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.8.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.9.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.9.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.9.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.9.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.9.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.9.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.10.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.10.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.10.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.10.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.10.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.10.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.11.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.11.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.11.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.11.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.11.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.11.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.12.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.12.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.12.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.12.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.12.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.12.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.13.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.13.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.13.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.13.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.13.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.13.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.14.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.14.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.14.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.14.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.14.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.14.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.15.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.15.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.15.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.15.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.15.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.15.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.16.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.16.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.16.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.16.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.16.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.16.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.17.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.17.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.17.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.17.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.17.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.17.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.18.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.18.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.18.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.18.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.18.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.18.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.19.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.19.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.19.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.19.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.19.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.19.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.20.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.20.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.20.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.20.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.20.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.20.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.21.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.21.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.21.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.21.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.21.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.21.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.22.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.22.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.22.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.22.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.22.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.22.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer4.0.conv1.weight: copying a param with shape torch.Size([512, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([832, 1024, 1, 1]).
size mismatch for layer4.0.bn1.weight: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([832]).
size mismatch for layer4.0.bn1.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([832]).
size mismatch for layer4.0.bn1.running_mean: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([832]).
size mismatch for layer4.0.bn1.running_var: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([832]).
size mismatch for layer4.0.conv3.weight: copying a param with shape torch.Size([2048, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([2048, 832, 1, 1]).
size mismatch for layer4.1.conv1.weight: copying a param with shape torch.Size([512, 2048, 1, 1]) from checkpoint, the shape in current model is torch.Size([832, 2048, 1, 1]).
size mismatch for layer4.1.bn1.weight: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([832]).
size mismatch for layer4.1.bn1.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([832]).
size mismatch for layer4.1.bn1.running_mean: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([832]).
size mismatch for layer4.1.bn1.running_var: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([832]).
size mismatch for layer4.1.conv3.weight: copying a param with shape torch.Size([2048, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([2048, 832, 1, 1]).
size mismatch for layer4.2.conv1.weight: copying a param with shape torch.Size([512, 2048, 1, 1]) from checkpoint, the shape in current model is torch.Size([832, 2048, 1, 1]).
size mismatch for layer4.2.bn1.weight: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([832]).
size mismatch for layer4.2.bn1.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([832]).
size mismatch for layer4.2.bn1.running_mean: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([832]).
size mismatch for layer4.2.bn1.running_var: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([832]).
size mismatch for layer4.2.conv3.weight: #copying a param with shape torch.Size([2048, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([2048, 832, 1, 1]).

@gasvn
Copy link
Member

gasvn commented Sep 16, 2019

I have tested the model downloaded from Onedirve, and it works fine. My testing code is :

from res2net import res2net101_26w_4s
model = res2net101_26w_4s(pretrained=True)
print(model)

I put the res2net101_26w_4s-02a759a1.pth model into the default path of pretrained models, in my case is /home/shanghuagao/.cache/torch/checkpoints/.
I assume that you might mistakenly use the pretrained model or model definition of ResNet.

@gasvn gasvn closed this as completed Sep 16, 2019
@mathpopo
Copy link

Hi, the error is as follows:

RuntimeError: Error(s) in loading state_dict for Res2Net:
Missing key(s) in state_dict: "layer1.0.convs.0.weight", "layer1.0.convs.1.weight", "layer1.0.convs.2.weight", "layer1.0.bns.0.weight", "layer1.0.bns.0.bias", "layer1.0.bns.0.running_mean", "layer1.0.bns.0.running_var", "layer1.0.bns.1.weight", "layer1.0.bns.1.bias", "layer1.0.bns.1.running_mean", "layer1.0.bns.1.running_var", "layer1.0.bns.2.weight", "layer1.0.bns.2.bias", "layer1.0.bns.2.running_mean", "layer1.0.bns.2.running_var", "layer1.1.convs.0.weight", "layer1.1.convs.1.weight", "layer1.1.convs.2.weight", "layer1.1.bns.0.weight", "layer1.1.bns.0.bias", "layer1.1.bns.0.running_mean", "layer1.1.bns.0.running_var", "layer1.1.bns.1.weight", "layer1.1.bns.1.bias", "layer1.1.bns.1.running_mean", "layer1.1.bns.1.running_var", "layer1.1.bns.2.weight", "layer1.1.bns.2.bias", "layer1.1.bns.2.running_mean", "layer1.1.bns.2.running_var", "layer1.2.convs.0.weight", "layer1.2.convs.1.weight", "layer1.2.convs.2.weight", "layer1.2.bns.0.weight", "layer1.2.bns.0.bias", "layer1.2.bns.0.running_mean", "layer1.2.bns.0.running_var", "layer1.2.bns.1.weight", "layer1.2.bns.1.bias", "layer1.2.bns.1.running_mean", "layer1.2.bns.1.running_var", "layer1.2.bns.2.weight", "layer1.2.bns.2.bias", "layer1.2.bns.2.running_mean", "layer1.2.bns.2.running_var", "layer2.0.convs.0.weight", "layer2.0.convs.1.weight", "layer2.0.convs.2.weight", "layer2.0.bns.0.weight", "layer2.0.bns.0.bias", "layer2.0.bns.0.running_mean", "layer2.0.bns.0.running_var", "layer2.0.bns.1.weight", "layer2.0.bns.1.bias", "layer2.0.bns.1.running_mean", "layer2.0.bns.1.running_var", "layer2.0.bns.2.weight", "layer2.0.bns.2.bias", "layer2.0.bns.2.running_mean", "layer2.0.bns.2.running_var", "layer2.1.convs.0.weight", "layer2.1.convs.1.weight", "layer2.1.convs.2.weight", "layer2.1.bns.0.weight", "layer2.1.bns.0.bias", "layer2.1.bns.0.running_mean", "layer2.1.bns.0.running_var", "layer2.1.bns.1.weight", "layer2.1.bns.1.bias", "layer2.1.bns.1.running_mean", "layer2.1.bns.1.running_var", "layer2.1.bns.2.weight", "layer2.1.bns.2.bias", "layer2.1.bns.2.running_mean", "layer2.1.bns.2.running_var", "layer2.2.convs.0.weight", "layer2.2.convs.1.weight", "layer2.2.convs.2.weight", "layer2.2.bns.0.weight", "layer2.2.bns.0.bias", "layer2.2.bns.0.running_mean", "layer2.2.bns.0.running_var", "layer2.2.bns.1.weight", "layer2.2.bns.1.bias", "layer2.2.bns.1.running_mean", "layer2.2.bns.1.running_var", "layer2.2.bns.2.weight", "layer2.2.bns.2.bias", "layer2.2.bns.2.running_mean", "layer2.2.bns.2.running_var", "layer2.3.convs.0.weight", "layer2.3.convs.1.weight", "layer2.3.convs.2.weight", "layer2.3.bns.0.weight", "layer2.3.bns.0.bias", "layer2.3.bns.0.running_mean", "layer2.3.bns.0.running_var", "layer2.3.bns.1.weight", "layer2.3.bns.1.bias", "layer2.3.bns.1.running_mean", "layer2.3.bns.1.running_var", "layer2.3.bns.2.weight", "layer2.3.bns.2.bias", "layer2.3.bns.2.running_mean", "layer2.3.bns.2.running_var", "layer3.0.convs.0.weight", "layer3.0.convs.1.weight", "layer3.0.convs.2.weight", "layer3.0.bns.0.weight", "layer3.0.bns.0.bias", "layer3.0.bns.0.running_mean", "layer3.0.bns.0.running_var", "layer3.0.bns.1.weight", "layer3.0.bns.1.bias", "layer3.0.bns.1.running_mean", "layer3.0.bns.1.running_var", "layer3.0.bns.2.weight", "layer3.0.bns.2.bias", "layer3.0.bns.2.running_mean", "layer3.0.bns.2.running_var", "layer3.1.convs.0.weight", "layer3.1.convs.1.weight", "layer3.1.convs.2.weight", "layer3.1.bns.0.weight", "layer3.1.bns.0.bias", "layer3.1.bns.0.running_mean", "layer3.1.bns.0.running_var", "layer3.1.bns.1.weight", "layer3.1.bns.1.bias", "layer3.1.bns.1.running_mean", "layer3.1.bns.1.running_var", "layer3.1.bns.2.weight", "layer3.1.bns.2.bias", "layer3.1.bns.2.running_mean", "layer3.1.bns.2.running_var", "layer3.2.convs.0.weight", "layer3.2.convs.1.weight", "layer3.2.convs.2.weight", "layer3.2.bns.0.weight", "layer3.2.bns.0.bias", "layer3.2.bns.0.running_mean", "layer3.2.bns.0.running_var", "layer3.2.bns.1.weight", "layer3.2.bns.1.bias", "layer3.2.bns.1.running_mean", "layer3.2.bns.1.running_var", "layer3.2.bns.2.weight", "layer3.2.bns.2.bias", "layer3.2.bns.2.running_mean", "layer3.2.bns.2.running_var", "layer3.3.convs.0.weight", "layer3.3.convs.1.weight", "layer3.3.convs.2.weight", "layer3.3.bns.0.weight", "layer3.3.bns.0.bias", "layer3.3.bns.0.running_mean", "layer3.3.bns.0.running_var", "layer3.3.bns.1.weight", "layer3.3.bns.1.bias", "layer3.3.bns.1.running_mean", "layer3.3.bns.1.running_var", "layer3.3.bns.2.weight", "layer3.3.bns.2.bias", "layer3.3.bns.2.running_mean", "layer3.3.bns.2.running_var", "layer3.4.convs.0.weight", "layer3.4.convs.1.weight", "layer3.4.convs.2.weight", "layer3.4.bns.0.weight", "layer3.4.bns.0.bias", "layer3.4.bns.0.running_mean", "layer3.4.bns.0.running_var", "layer3.4.bns.1.weight", "layer3.4.bns.1.bias", "layer3.4.bns.1.running_mean", "layer3.4.bns.1.running_var", "layer3.4.bns.2.weight", "layer3.4.bns.2.bias", "layer3.4.bns.2.running_mean", "layer3.4.bns.2.running_var", "layer3.5.convs.0.weight", "layer3.5.convs.1.weight", "layer3.5.convs.2.weight", "layer3.5.bns.0.weight", "layer3.5.bns.0.bias", "layer3.5.bns.0.running_mean", "layer3.5.bns.0.running_var", "layer3.5.bns.1.weight", "layer3.5.bns.1.bias", "layer3.5.bns.1.running_mean", "layer3.5.bns.1.running_var", "layer3.5.bns.2.weight", "layer3.5.bns.2.bias", "layer3.5.bns.2.running_mean", "layer3.5.bns.2.running_var", "layer3.6.convs.0.weight", "layer3.6.convs.1.weight", "layer3.6.convs.2.weight", "layer3.6.bns.0.weight", "layer3.6.bns.0.bias", "layer3.6.bns.0.running_mean", "layer3.6.bns.0.running_var", "layer3.6.bns.1.weight", "layer3.6.bns.1.bias", "layer3.6.bns.1.running_mean", "layer3.6.bns.1.running_var", "layer3.6.bns.2.weight", "layer3.6.bns.2.bias", "layer3.6.bns.2.running_mean", "layer3.6.bns.2.running_var", "layer3.7.convs.0.weight", "layer3.7.convs.1.weight", "layer3.7.convs.2.weight", "layer3.7.bns.0.weight", "layer3.7.bns.0.bias", "layer3.7.bns.0.running_mean", "layer3.7.bns.0.running_var", "layer3.7.bns.1.weight", "layer3.7.bns.1.bias", "layer3.7.bns.1.running_mean", "layer3.7.bns.1.running_var", "layer3.7.bns.2.weight", "layer3.7.bns.2.bias", "layer3.7.bns.2.running_mean", "layer3.7.bns.2.running_var", "layer3.8.convs.0.weight", "layer3.8.convs.1.weight", "layer3.8.convs.2.weight", "layer3.8.bns.0.weight", "layer3.8.bns.0.bias", "layer3.8.bns.0.running_mean", "layer3.8.bns.0.running_var", "layer3.8.bns.1.weight", "layer3.8.bns.1.bias", "layer3.8.bns.1.running_mean", "layer3.8.bns.1.running_var", "layer3.8.bns.2.weight", "layer3.8.bns.2.bias", "layer3.8.bns.2.running_mean", "layer3.8.bns.2.running_var", "layer3.9.convs.0.weight", "layer3.9.convs.1.weight", "layer3.9.convs.2.weight", "layer3.9.bns.0.weight", "layer3.9.bns.0.bias", "layer3.9.bns.0.running_mean", "layer3.9.bns.0.running_var", "layer3.9.bns.1.weight", "layer3.9.bns.1.bias", "layer3.9.bns.1.running_mean", "layer3.9.bns.1.running_var", "layer3.9.bns.2.weight", "layer3.9.bns.2.bias", "layer3.9.bns.2.running_mean", "layer3.9.bns.2.running_var", "layer3.10.convs.0.weight", "layer3.10.convs.1.weight", "layer3.10.convs.2.weight", "layer3.10.bns.0.weight", "layer3.10.bns.0.bias", "layer3.10.bns.0.running_mean", "layer3.10.bns.0.running_var", "layer3.10.bns.1.weight", "layer3.10.bns.1.bias", "layer3.10.bns.1.running_mean", "layer3.10.bns.1.running_var", "layer3.10.bns.2.weight", "layer3.10.bns.2.bias", "layer3.10.bns.2.running_mean", "layer3.10.bns.2.running_var", "layer3.11.convs.0.weight", "layer3.11.convs.1.weight", "layer3.11.convs.2.weight", "layer3.11.bns.0.weight", "layer3.11.bns.0.bias", "layer3.11.bns.0.running_mean", "layer3.11.bns.0.running_var", "layer3.11.bns.1.weight", "layer3.11.bns.1.bias", "layer3.11.bns.1.running_mean", "layer3.11.bns.1.running_var", "layer3.11.bns.2.weight", "layer3.11.bns.2.bias", "layer3.11.bns.2.running_mean", "layer3.11.bns.2.running_var", "layer3.12.convs.0.weight", "layer3.12.convs.1.weight", "layer3.12.convs.2.weight", "layer3.12.bns.0.weight", "layer3.12.bns.0.bias", "layer3.12.bns.0.running_mean", "layer3.12.bns.0.running_var", "layer3.12.bns.1.weight", "layer3.12.bns.1.bias", "layer3.12.bns.1.running_mean", "layer3.12.bns.1.running_var", "layer3.12.bns.2.weight", "layer3.12.bns.2.bias", "layer3.12.bns.2.running_mean", "layer3.12.bns.2.running_var", "layer3.13.convs.0.weight", "layer3.13.convs.1.weight", "layer3.13.convs.2.weight", "layer3.13.bns.0.weight", "layer3.13.bns.0.bias", "layer3.13.bns.0.running_mean", "layer3.13.bns.0.running_var", "layer3.13.bns.1.weight", "layer3.13.bns.1.bias", "layer3.13.bns.1.running_mean", "layer3.13.bns.1.running_var", "layer3.13.bns.2.weight", "layer3.13.bns.2.bias", "layer3.13.bns.2.running_mean", "layer3.13.bns.2.running_var", "layer3.14.convs.0.weight", "layer3.14.convs.1.weight", "layer3.14.convs.2.weight", "layer3.14.bns.0.weight", "layer3.14.bns.0.bias", "layer3.14.bns.0.running_mean", "layer3.14.bns.0.running_var", "layer3.14.bns.1.weight", "layer3.14.bns.1.bias", "layer3.14.bns.1.running_mean", "layer3.14.bns.1.running_var", "layer3.14.bns.2.weight", "layer3.14.bns.2.bias", "layer3.14.bns.2.running_mean", "layer3.14.bns.2.running_var", "layer3.15.convs.0.weight", "layer3.15.convs.1.weight", "layer3.15.convs.2.weight", "layer3.15.bns.0.weight", "layer3.15.bns.0.bias", "layer3.15.bns.0.running_mean", "layer3.15.bns.0.running_var", "layer3.15.bns.1.weight", "layer3.15.bns.1.bias", "layer3.15.bns.1.running_mean", "layer3.15.bns.1.running_var", "layer3.15.bns.2.weight", "layer3.15.bns.2.bias", "layer3.15.bns.2.running_mean", "layer3.15.bns.2.running_var", "layer3.16.convs.0.weight", "layer3.16.convs.1.weight", "layer3.16.convs.2.weight", "layer3.16.bns.0.weight", "layer3.16.bns.0.bias", "layer3.16.bns.0.running_mean", "layer3.16.bns.0.running_var", "layer3.16.bns.1.weight", "layer3.16.bns.1.bias", "layer3.16.bns.1.running_mean", "layer3.16.bns.1.running_var", "layer3.16.bns.2.weight", "layer3.16.bns.2.bias", "layer3.16.bns.2.running_mean", "layer3.16.bns.2.running_var", "layer3.17.convs.0.weight", "layer3.17.convs.1.weight", "layer3.17.convs.2.weight", "layer3.17.bns.0.weight", "layer3.17.bns.0.bias", "layer3.17.bns.0.running_mean", "layer3.17.bns.0.running_var", "layer3.17.bns.1.weight", "layer3.17.bns.1.bias", "layer3.17.bns.1.running_mean", "layer3.17.bns.1.running_var", "layer3.17.bns.2.weight", "layer3.17.bns.2.bias", "layer3.17.bns.2.running_mean", "layer3.17.bns.2.running_var", "layer3.18.convs.0.weight", "layer3.18.convs.1.weight", "layer3.18.convs.2.weight", "layer3.18.bns.0.weight", "layer3.18.bns.0.bias", "layer3.18.bns.0.running_mean", "layer3.18.bns.0.running_var", "layer3.18.bns.1.weight", "layer3.18.bns.1.bias", "layer3.18.bns.1.running_mean", "layer3.18.bns.1.running_var", "layer3.18.bns.2.weight", "layer3.18.bns.2.bias", "layer3.18.bns.2.running_mean", "layer3.18.bns.2.running_var", "layer3.19.convs.0.weight", "layer3.19.convs.1.weight", "layer3.19.convs.2.weight", "layer3.19.bns.0.weight", "layer3.19.bns.0.bias", "layer3.19.bns.0.running_mean", "layer3.19.bns.0.running_var", "layer3.19.bns.1.weight", "layer3.19.bns.1.bias", "layer3.19.bns.1.running_mean", "layer3.19.bns.1.running_var", "layer3.19.bns.2.weight", "layer3.19.bns.2.bias", "layer3.19.bns.2.running_mean", "layer3.19.bns.2.running_var", "layer3.20.convs.0.weight", "layer3.20.convs.1.weight", "layer3.20.convs.2.weight", "layer3.20.bns.0.weight", "layer3.20.bns.0.bias", "layer3.20.bns.0.running_mean", "layer3.20.bns.0.running_var", "layer3.20.bns.1.weight", "layer3.20.bns.1.bias", "layer3.20.bns.1.running_mean", "layer3.20.bns.1.running_var", "layer3.20.bns.2.weight", "layer3.20.bns.2.bias", "layer3.20.bns.2.running_mean", "layer3.20.bns.2.running_var", "layer3.21.convs.0.weight", "layer3.21.convs.1.weight", "layer3.21.convs.2.weight", "layer3.21.bns.0.weight", "layer3.21.bns.0.bias", "layer3.21.bns.0.running_mean", "layer3.21.bns.0.running_var", "layer3.21.bns.1.weight", "layer3.21.bns.1.bias", "layer3.21.bns.1.running_mean", "layer3.21.bns.1.running_var", "layer3.21.bns.2.weight", "layer3.21.bns.2.bias", "layer3.21.bns.2.running_mean", "layer3.21.bns.2.running_var", "layer3.22.convs.0.weight", "layer3.22.convs.1.weight", "layer3.22.convs.2.weight", "layer3.22.bns.0.weight", "layer3.22.bns.0.bias", "layer3.22.bns.0.running_mean", "layer3.22.bns.0.running_var", "layer3.22.bns.1.weight", "layer3.22.bns.1.bias", "layer3.22.bns.1.running_mean", "layer3.22.bns.1.running_var", "layer3.22.bns.2.weight", "layer3.22.bns.2.bias", "layer3.22.bns.2.running_mean", "layer3.22.bns.2.running_var", "layer4.0.convs.0.weight", "layer4.0.convs.1.weight", "layer4.0.convs.2.weight", "layer4.0.bns.0.weight", "layer4.0.bns.0.bias", "layer4.0.bns.0.running_mean", "layer4.0.bns.0.running_var", "layer4.0.bns.1.weight", "layer4.0.bns.1.bias", "layer4.0.bns.1.running_mean", "layer4.0.bns.1.running_var", "layer4.0.bns.2.weight", "layer4.0.bns.2.bias", "layer4.0.bns.2.running_mean", "layer4.0.bns.2.running_var", "layer4.1.convs.0.weight", "layer4.1.convs.1.weight", "layer4.1.convs.2.weight", "layer4.1.bns.0.weight", "layer4.1.bns.0.bias", "layer4.1.bns.0.running_mean", "layer4.1.bns.0.running_var", "layer4.1.bns.1.weight", "layer4.1.bns.1.bias", "layer4.1.bns.1.running_mean", "layer4.1.bns.1.running_var", "layer4.1.bns.2.weight", "layer4.1.bns.2.bias", "layer4.1.bns.2.running_mean", "layer4.1.bns.2.running_var", "layer4.2.convs.0.weight", "layer4.2.convs.1.weight", "layer4.2.convs.2.weight", "layer4.2.bns.0.weight", "layer4.2.bns.0.bias", "layer4.2.bns.0.running_mean", "layer4.2.bns.0.running_var", "layer4.2.bns.1.weight", "layer4.2.bns.1.bias", "layer4.2.bns.1.running_mean", "layer4.2.bns.1.running_var", "layer4.2.bns.2.weight", "layer4.2.bns.2.bias", "layer4.2.bns.2.running_mean", "layer4.2.bns.2.running_var".
Unexpected key(s) in state_dict: "layer1.0.conv2.weight", "layer1.0.bn2.running_mean", "layer1.0.bn2.running_var", "layer1.0.bn2.weight", "layer1.0.bn2.bias", "layer1.1.conv2.weight", "layer1.1.bn2.running_mean", "layer1.1.bn2.running_var", "layer1.1.bn2.weight", "layer1.1.bn2.bias", "layer1.2.conv2.weight", "layer1.2.bn2.running_mean", "layer1.2.bn2.running_var", "layer1.2.bn2.weight", "layer1.2.bn2.bias", "layer2.0.conv2.weight", "layer2.0.bn2.running_mean", "layer2.0.bn2.running_var", "layer2.0.bn2.weight", "layer2.0.bn2.bias", "layer2.1.conv2.weight", "layer2.1.bn2.running_mean", "layer2.1.bn2.running_var", "layer2.1.bn2.weight", "layer2.1.bn2.bias", "layer2.2.conv2.weight", "layer2.2.bn2.running_mean", "layer2.2.bn2.running_var", "layer2.2.bn2.weight", "layer2.2.bn2.bias", "layer2.3.conv2.weight", "layer2.3.bn2.running_mean", "layer2.3.bn2.running_var", "layer2.3.bn2.weight", "layer2.3.bn2.bias", "layer3.0.conv2.weight", "layer3.0.bn2.running_mean", "layer3.0.bn2.running_var", "layer3.0.bn2.weight", "layer3.0.bn2.bias", "layer3.1.conv2.weight", "layer3.1.bn2.running_mean", "layer3.1.bn2.running_var", "layer3.1.bn2.weight", "layer3.1.bn2.bias", "layer3.2.conv2.weight", "layer3.2.bn2.running_mean", "layer3.2.bn2.running_var", "layer3.2.bn2.weight", "layer3.2.bn2.bias", "layer3.3.conv2.weight", "layer3.3.bn2.running_mean", "layer3.3.bn2.running_var", "layer3.3.bn2.weight", "layer3.3.bn2.bias", "layer3.4.conv2.weight", "layer3.4.bn2.running_mean", "layer3.4.bn2.running_var", "layer3.4.bn2.weight", "layer3.4.bn2.bias", "layer3.5.conv2.weight", "layer3.5.bn2.running_mean", "layer3.5.bn2.running_var", "layer3.5.bn2.weight", "layer3.5.bn2.bias", "layer3.6.conv2.weight", "layer3.6.bn2.running_mean", "layer3.6.bn2.running_var", "layer3.6.bn2.weight", "layer3.6.bn2.bias", "layer3.7.conv2.weight", "layer3.7.bn2.running_mean", "layer3.7.bn2.running_var", "layer3.7.bn2.weight", "layer3.7.bn2.bias", "layer3.8.conv2.weight", "layer3.8.bn2.running_mean", "layer3.8.bn2.running_var", "layer3.8.bn2.weight", "layer3.8.bn2.bias", "layer3.9.conv2.weight", "layer3.9.bn2.running_mean", "layer3.9.bn2.running_var", "layer3.9.bn2.weight", "layer3.9.bn2.bias", "layer3.10.conv2.weight", "layer3.10.bn2.running_mean", "layer3.10.bn2.running_var", "layer3.10.bn2.weight", "layer3.10.bn2.bias", "layer3.11.conv2.weight", "layer3.11.bn2.running_mean", "layer3.11.bn2.running_var", "layer3.11.bn2.weight", "layer3.11.bn2.bias", "layer3.12.conv2.weight", "layer3.12.bn2.running_mean", "layer3.12.bn2.running_var", "layer3.12.bn2.weight", "layer3.12.bn2.bias", "layer3.13.conv2.weight", "layer3.13.bn2.running_mean", "layer3.13.bn2.running_var", "layer3.13.bn2.weight", "layer3.13.bn2.bias", "layer3.14.conv2.weight", "layer3.14.bn2.running_mean", "layer3.14.bn2.running_var", "layer3.14.bn2.weight", "layer3.14.bn2.bias", "layer3.15.conv2.weight", "layer3.15.bn2.running_mean", "layer3.15.bn2.running_var", "layer3.15.bn2.weight", "layer3.15.bn2.bias", "layer3.16.conv2.weight", "layer3.16.bn2.running_mean", "layer3.16.bn2.running_var", "layer3.16.bn2.weight", "layer3.16.bn2.bias", "layer3.17.conv2.weight", "layer3.17.bn2.running_mean", "layer3.17.bn2.running_var", "layer3.17.bn2.weight", "layer3.17.bn2.bias", "layer3.18.conv2.weight", "layer3.18.bn2.running_mean", "layer3.18.bn2.running_var", "layer3.18.bn2.weight", "layer3.18.bn2.bias", "layer3.19.conv2.weight", "layer3.19.bn2.running_mean", "layer3.19.bn2.running_var", "layer3.19.bn2.weight", "layer3.19.bn2.bias", "layer3.20.conv2.weight", "layer3.20.bn2.running_mean", "layer3.20.bn2.running_var", "layer3.20.bn2.weight", "layer3.20.bn2.bias", "layer3.21.conv2.weight", "layer3.21.bn2.running_mean", "layer3.21.bn2.running_var", "layer3.21.bn2.weight", "layer3.21.bn2.bias", "layer3.22.conv2.weight", "layer3.22.bn2.running_mean", "layer3.22.bn2.running_var", "layer3.22.bn2.weight", "layer3.22.bn2.bias", "layer4.0.conv2.weight", "layer4.0.bn2.running_mean", "layer4.0.bn2.running_var", "layer4.0.bn2.weight", "layer4.0.bn2.bias", "layer4.1.conv2.weight", "layer4.1.bn2.running_mean", "layer4.1.bn2.running_var", "layer4.1.bn2.weight", "layer4.1.bn2.bias", "layer4.2.conv2.weight", "layer4.2.bn2.running_mean", "layer4.2.bn2.running_var", "layer4.2.bn2.weight", "layer4.2.bn2.bias".
size mismatch for layer1.0.conv1.weight: copying a param with shape torch.Size([64, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([104, 64, 1, 1]).
size mismatch for layer1.0.bn1.weight: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([104]).
size mismatch for layer1.0.bn1.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([104]).
size mismatch for layer1.0.bn1.running_mean: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([104]).
size mismatch for layer1.0.bn1.running_var: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([104]).
size mismatch for layer1.0.conv3.weight: copying a param with shape torch.Size([256, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 104, 1, 1]).
size mismatch for layer1.1.conv1.weight: copying a param with shape torch.Size([64, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([104, 256, 1, 1]).
size mismatch for layer1.1.bn1.weight: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([104]).
size mismatch for layer1.1.bn1.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([104]).
size mismatch for layer1.1.bn1.running_mean: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([104]).
size mismatch for layer1.1.bn1.running_var: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([104]).
size mismatch for layer1.1.conv3.weight: copying a param with shape torch.Size([256, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 104, 1, 1]).
size mismatch for layer1.2.conv1.weight: copying a param with shape torch.Size([64, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([104, 256, 1, 1]).
size mismatch for layer1.2.bn1.weight: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([104]).
size mismatch for layer1.2.bn1.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([104]).
size mismatch for layer1.2.bn1.running_mean: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([104]).
size mismatch for layer1.2.bn1.running_var: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([104]).
size mismatch for layer1.2.conv3.weight: copying a param with shape torch.Size([256, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 104, 1, 1]).
size mismatch for layer2.0.conv1.weight: copying a param with shape torch.Size([128, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([208, 256, 1, 1]).
size mismatch for layer2.0.bn1.weight: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.0.bn1.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.0.bn1.running_mean: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.0.bn1.running_var: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.0.conv3.weight: copying a param with shape torch.Size([512, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([512, 208, 1, 1]).
size mismatch for layer2.1.conv1.weight: copying a param with shape torch.Size([128, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([208, 512, 1, 1]).
size mismatch for layer2.1.bn1.weight: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.1.bn1.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.1.bn1.running_mean: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.1.bn1.running_var: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.1.conv3.weight: copying a param with shape torch.Size([512, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([512, 208, 1, 1]).
size mismatch for layer2.2.conv1.weight: copying a param with shape torch.Size([128, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([208, 512, 1, 1]).
size mismatch for layer2.2.bn1.weight: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.2.bn1.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.2.bn1.running_mean: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.2.bn1.running_var: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.2.conv3.weight: copying a param with shape torch.Size([512, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([512, 208, 1, 1]).
size mismatch for layer2.3.conv1.weight: copying a param with shape torch.Size([128, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([208, 512, 1, 1]).
size mismatch for layer2.3.bn1.weight: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.3.bn1.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.3.bn1.running_mean: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.3.bn1.running_var: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.3.conv3.weight: copying a param with shape torch.Size([512, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([512, 208, 1, 1]).
size mismatch for layer3.0.conv1.weight: copying a param with shape torch.Size([256, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 512, 1, 1]).
size mismatch for layer3.0.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.0.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.0.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.0.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.0.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.1.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.1.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.1.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.1.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.1.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.1.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.2.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.2.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.2.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.2.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.2.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.2.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.3.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.3.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.3.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.3.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.3.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.3.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.4.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.4.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.4.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.4.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.4.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.4.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.5.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.5.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.5.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.5.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.5.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.5.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.6.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.6.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.6.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.6.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.6.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.6.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.7.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.7.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.7.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.7.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.7.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.7.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.8.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.8.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.8.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.8.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.8.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.8.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.9.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.9.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.9.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.9.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.9.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.9.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.10.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.10.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.10.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.10.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.10.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.10.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.11.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.11.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.11.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.11.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.11.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.11.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.12.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.12.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.12.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.12.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.12.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.12.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.13.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.13.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.13.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.13.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.13.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.13.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.14.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.14.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.14.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.14.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.14.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.14.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.15.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.15.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.15.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.15.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.15.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.15.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.16.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.16.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.16.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.16.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.16.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.16.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.17.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.17.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.17.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.17.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.17.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.17.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.18.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.18.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.18.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.18.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.18.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.18.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.19.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.19.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.19.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.19.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.19.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.19.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.20.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.20.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.20.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.20.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.20.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.20.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.21.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.21.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.21.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.21.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.21.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.21.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.22.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.22.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.22.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.22.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.22.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.22.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer4.0.conv1.weight: copying a param with shape torch.Size([512, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([832, 1024, 1, 1]).
size mismatch for layer4.0.bn1.weight: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([832]).
size mismatch for layer4.0.bn1.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([832]).
size mismatch for layer4.0.bn1.running_mean: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([832]).
size mismatch for layer4.0.bn1.running_var: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([832]).
size mismatch for layer4.0.conv3.weight: copying a param with shape torch.Size([2048, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([2048, 832, 1, 1]).
size mismatch for layer4.1.conv1.weight: copying a param with shape torch.Size([512, 2048, 1, 1]) from checkpoint, the shape in current model is torch.Size([832, 2048, 1, 1]).
size mismatch for layer4.1.bn1.weight: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([832]).
size mismatch for layer4.1.bn1.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([832]).
size mismatch for layer4.1.bn1.running_mean: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([832]).
size mismatch for layer4.1.bn1.running_var: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([832]).
size mismatch for layer4.1.conv3.weight: copying a param with shape torch.Size([2048, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([2048, 832, 1, 1]).
size mismatch for layer4.2.conv1.weight: copying a param with shape torch.Size([512, 2048, 1, 1]) from checkpoint, the shape in current model is torch.Size([832, 2048, 1, 1]).
size mismatch for layer4.2.bn1.weight: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([832]).
size mismatch for layer4.2.bn1.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([832]).
size mismatch for layer4.2.bn1.running_mean: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([832]).
size mismatch for layer4.2.bn1.running_var: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([832]).
size mismatch for layer4.2.conv3.weight: #copying a param with shape torch.Size([2048, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([2048, 832, 1, 1]).

hi . i have the same issue,canyou reslove it?

@RLiBIn
Copy link

RLiBIn commented Mar 9, 2020

i have the same problem.but i have solve it. you don't change the .yaml file.one word,it work.
i add TEST_PERIOD: 10000 model.it don't work.I am thinking the problem.if you solve ,please contact me.

@gasvn
Copy link
Member

gasvn commented Mar 9, 2020

Hi, the error is as follows:
RuntimeError: Error(s) in loading state_dict for Res2Net:
Missing key(s) in state_dict: "layer1.0.convs.0.weight", "layer1.0.convs.1.weight", "layer1.0.convs.2.weight", "layer1.0.bns.0.weight", "layer1.0.bns.0.bias", "layer1.0.bns.0.running_mean", "layer1.0.bns.0.running_var", "layer1.0.bns.1.weight", "layer1.0.bns.1.bias", "layer1.0.bns.1.running_mean", "layer1.0.bns.1.running_var", "layer1.0.bns.2.weight", "layer1.0.bns.2.bias", "layer1.0.bns.2.running_mean", "layer1.0.bns.2.running_var", "layer1.1.convs.0.weight", "layer1.1.convs.1.weight", "layer1.1.convs.2.weight", "layer1.1.bns.0.weight", "layer1.1.bns.0.bias", "layer1.1.bns.0.running_mean", "layer1.1.bns.0.running_var", "layer1.1.bns.1.weight", "layer1.1.bns.1.bias", "layer1.1.bns.1.running_mean", "layer1.1.bns.1.running_var", "layer1.1.bns.2.weight", "layer1.1.bns.2.bias", "layer1.1.bns.2.running_mean", "layer1.1.bns.2.running_var", "layer1.2.convs.0.weight", "layer1.2.convs.1.weight", "layer1.2.convs.2.weight", "layer1.2.bns.0.weight", "layer1.2.bns.0.bias", "layer1.2.bns.0.running_mean", "layer1.2.bns.0.running_var", "layer1.2.bns.1.weight", "layer1.2.bns.1.bias", "layer1.2.bns.1.running_mean", "layer1.2.bns.1.running_var", "layer1.2.bns.2.weight", "layer1.2.bns.2.bias", "layer1.2.bns.2.running_mean", "layer1.2.bns.2.running_var", "layer2.0.convs.0.weight", "layer2.0.convs.1.weight", "layer2.0.convs.2.weight", "layer2.0.bns.0.weight", "layer2.0.bns.0.bias", "layer2.0.bns.0.running_mean", "layer2.0.bns.0.running_var", "layer2.0.bns.1.weight", "layer2.0.bns.1.bias", "layer2.0.bns.1.running_mean", "layer2.0.bns.1.running_var", "layer2.0.bns.2.weight", "layer2.0.bns.2.bias", "layer2.0.bns.2.running_mean", "layer2.0.bns.2.running_var", "layer2.1.convs.0.weight", "layer2.1.convs.1.weight", "layer2.1.convs.2.weight", "layer2.1.bns.0.weight", "layer2.1.bns.0.bias", "layer2.1.bns.0.running_mean", "layer2.1.bns.0.running_var", "layer2.1.bns.1.weight", "layer2.1.bns.1.bias", "layer2.1.bns.1.running_mean", "layer2.1.bns.1.running_var", "layer2.1.bns.2.weight", "layer2.1.bns.2.bias", "layer2.1.bns.2.running_mean", "layer2.1.bns.2.running_var", "layer2.2.convs.0.weight", "layer2.2.convs.1.weight", "layer2.2.convs.2.weight", "layer2.2.bns.0.weight", "layer2.2.bns.0.bias", "layer2.2.bns.0.running_mean", "layer2.2.bns.0.running_var", "layer2.2.bns.1.weight", "layer2.2.bns.1.bias", "layer2.2.bns.1.running_mean", "layer2.2.bns.1.running_var", "layer2.2.bns.2.weight", "layer2.2.bns.2.bias", "layer2.2.bns.2.running_mean", "layer2.2.bns.2.running_var", "layer2.3.convs.0.weight", "layer2.3.convs.1.weight", "layer2.3.convs.2.weight", "layer2.3.bns.0.weight", "layer2.3.bns.0.bias", "layer2.3.bns.0.running_mean", "layer2.3.bns.0.running_var", "layer2.3.bns.1.weight", "layer2.3.bns.1.bias", "layer2.3.bns.1.running_mean", "layer2.3.bns.1.running_var", "layer2.3.bns.2.weight", "layer2.3.bns.2.bias", "layer2.3.bns.2.running_mean", "layer2.3.bns.2.running_var", "layer3.0.convs.0.weight", "layer3.0.convs.1.weight", "layer3.0.convs.2.weight", "layer3.0.bns.0.weight", "layer3.0.bns.0.bias", "layer3.0.bns.0.running_mean", "layer3.0.bns.0.running_var", "layer3.0.bns.1.weight", "layer3.0.bns.1.bias", "layer3.0.bns.1.running_mean", "layer3.0.bns.1.running_var", "layer3.0.bns.2.weight", "layer3.0.bns.2.bias", "layer3.0.bns.2.running_mean", "layer3.0.bns.2.running_var", "layer3.1.convs.0.weight", "layer3.1.convs.1.weight", "layer3.1.convs.2.weight", "layer3.1.bns.0.weight", "layer3.1.bns.0.bias", "layer3.1.bns.0.running_mean", "layer3.1.bns.0.running_var", "layer3.1.bns.1.weight", "layer3.1.bns.1.bias", "layer3.1.bns.1.running_mean", "layer3.1.bns.1.running_var", "layer3.1.bns.2.weight", "layer3.1.bns.2.bias", "layer3.1.bns.2.running_mean", "layer3.1.bns.2.running_var", "layer3.2.convs.0.weight", "layer3.2.convs.1.weight", "layer3.2.convs.2.weight", "layer3.2.bns.0.weight", "layer3.2.bns.0.bias", "layer3.2.bns.0.running_mean", "layer3.2.bns.0.running_var", "layer3.2.bns.1.weight", "layer3.2.bns.1.bias", "layer3.2.bns.1.running_mean", "layer3.2.bns.1.running_var", "layer3.2.bns.2.weight", "layer3.2.bns.2.bias", "layer3.2.bns.2.running_mean", "layer3.2.bns.2.running_var", "layer3.3.convs.0.weight", "layer3.3.convs.1.weight", "layer3.3.convs.2.weight", "layer3.3.bns.0.weight", "layer3.3.bns.0.bias", "layer3.3.bns.0.running_mean", "layer3.3.bns.0.running_var", "layer3.3.bns.1.weight", "layer3.3.bns.1.bias", "layer3.3.bns.1.running_mean", "layer3.3.bns.1.running_var", "layer3.3.bns.2.weight", "layer3.3.bns.2.bias", "layer3.3.bns.2.running_mean", "layer3.3.bns.2.running_var", "layer3.4.convs.0.weight", "layer3.4.convs.1.weight", "layer3.4.convs.2.weight", "layer3.4.bns.0.weight", "layer3.4.bns.0.bias", "layer3.4.bns.0.running_mean", "layer3.4.bns.0.running_var", "layer3.4.bns.1.weight", "layer3.4.bns.1.bias", "layer3.4.bns.1.running_mean", "layer3.4.bns.1.running_var", "layer3.4.bns.2.weight", "layer3.4.bns.2.bias", "layer3.4.bns.2.running_mean", "layer3.4.bns.2.running_var", "layer3.5.convs.0.weight", "layer3.5.convs.1.weight", "layer3.5.convs.2.weight", "layer3.5.bns.0.weight", "layer3.5.bns.0.bias", "layer3.5.bns.0.running_mean", "layer3.5.bns.0.running_var", "layer3.5.bns.1.weight", "layer3.5.bns.1.bias", "layer3.5.bns.1.running_mean", "layer3.5.bns.1.running_var", "layer3.5.bns.2.weight", "layer3.5.bns.2.bias", "layer3.5.bns.2.running_mean", "layer3.5.bns.2.running_var", "layer3.6.convs.0.weight", "layer3.6.convs.1.weight", "layer3.6.convs.2.weight", "layer3.6.bns.0.weight", "layer3.6.bns.0.bias", "layer3.6.bns.0.running_mean", "layer3.6.bns.0.running_var", "layer3.6.bns.1.weight", "layer3.6.bns.1.bias", "layer3.6.bns.1.running_mean", "layer3.6.bns.1.running_var", "layer3.6.bns.2.weight", "layer3.6.bns.2.bias", "layer3.6.bns.2.running_mean", "layer3.6.bns.2.running_var", "layer3.7.convs.0.weight", "layer3.7.convs.1.weight", "layer3.7.convs.2.weight", "layer3.7.bns.0.weight", "layer3.7.bns.0.bias", "layer3.7.bns.0.running_mean", "layer3.7.bns.0.running_var", "layer3.7.bns.1.weight", "layer3.7.bns.1.bias", "layer3.7.bns.1.running_mean", "layer3.7.bns.1.running_var", "layer3.7.bns.2.weight", "layer3.7.bns.2.bias", "layer3.7.bns.2.running_mean", "layer3.7.bns.2.running_var", "layer3.8.convs.0.weight", "layer3.8.convs.1.weight", "layer3.8.convs.2.weight", "layer3.8.bns.0.weight", "layer3.8.bns.0.bias", "layer3.8.bns.0.running_mean", "layer3.8.bns.0.running_var", "layer3.8.bns.1.weight", "layer3.8.bns.1.bias", "layer3.8.bns.1.running_mean", "layer3.8.bns.1.running_var", "layer3.8.bns.2.weight", "layer3.8.bns.2.bias", "layer3.8.bns.2.running_mean", "layer3.8.bns.2.running_var", "layer3.9.convs.0.weight", "layer3.9.convs.1.weight", "layer3.9.convs.2.weight", "layer3.9.bns.0.weight", "layer3.9.bns.0.bias", "layer3.9.bns.0.running_mean", "layer3.9.bns.0.running_var", "layer3.9.bns.1.weight", "layer3.9.bns.1.bias", "layer3.9.bns.1.running_mean", "layer3.9.bns.1.running_var", "layer3.9.bns.2.weight", "layer3.9.bns.2.bias", "layer3.9.bns.2.running_mean", "layer3.9.bns.2.running_var", "layer3.10.convs.0.weight", "layer3.10.convs.1.weight", "layer3.10.convs.2.weight", "layer3.10.bns.0.weight", "layer3.10.bns.0.bias", "layer3.10.bns.0.running_mean", "layer3.10.bns.0.running_var", "layer3.10.bns.1.weight", "layer3.10.bns.1.bias", "layer3.10.bns.1.running_mean", "layer3.10.bns.1.running_var", "layer3.10.bns.2.weight", "layer3.10.bns.2.bias", "layer3.10.bns.2.running_mean", "layer3.10.bns.2.running_var", "layer3.11.convs.0.weight", "layer3.11.convs.1.weight", "layer3.11.convs.2.weight", "layer3.11.bns.0.weight", "layer3.11.bns.0.bias", "layer3.11.bns.0.running_mean", "layer3.11.bns.0.running_var", "layer3.11.bns.1.weight", "layer3.11.bns.1.bias", "layer3.11.bns.1.running_mean", "layer3.11.bns.1.running_var", "layer3.11.bns.2.weight", "layer3.11.bns.2.bias", "layer3.11.bns.2.running_mean", "layer3.11.bns.2.running_var", "layer3.12.convs.0.weight", "layer3.12.convs.1.weight", "layer3.12.convs.2.weight", "layer3.12.bns.0.weight", "layer3.12.bns.0.bias", "layer3.12.bns.0.running_mean", "layer3.12.bns.0.running_var", "layer3.12.bns.1.weight", "layer3.12.bns.1.bias", "layer3.12.bns.1.running_mean", "layer3.12.bns.1.running_var", "layer3.12.bns.2.weight", "layer3.12.bns.2.bias", "layer3.12.bns.2.running_mean", "layer3.12.bns.2.running_var", "layer3.13.convs.0.weight", "layer3.13.convs.1.weight", "layer3.13.convs.2.weight", "layer3.13.bns.0.weight", "layer3.13.bns.0.bias", "layer3.13.bns.0.running_mean", "layer3.13.bns.0.running_var", "layer3.13.bns.1.weight", "layer3.13.bns.1.bias", "layer3.13.bns.1.running_mean", "layer3.13.bns.1.running_var", "layer3.13.bns.2.weight", "layer3.13.bns.2.bias", "layer3.13.bns.2.running_mean", "layer3.13.bns.2.running_var", "layer3.14.convs.0.weight", "layer3.14.convs.1.weight", "layer3.14.convs.2.weight", "layer3.14.bns.0.weight", "layer3.14.bns.0.bias", "layer3.14.bns.0.running_mean", "layer3.14.bns.0.running_var", "layer3.14.bns.1.weight", "layer3.14.bns.1.bias", "layer3.14.bns.1.running_mean", "layer3.14.bns.1.running_var", "layer3.14.bns.2.weight", "layer3.14.bns.2.bias", "layer3.14.bns.2.running_mean", "layer3.14.bns.2.running_var", "layer3.15.convs.0.weight", "layer3.15.convs.1.weight", "layer3.15.convs.2.weight", "layer3.15.bns.0.weight", "layer3.15.bns.0.bias", "layer3.15.bns.0.running_mean", "layer3.15.bns.0.running_var", "layer3.15.bns.1.weight", "layer3.15.bns.1.bias", "layer3.15.bns.1.running_mean", "layer3.15.bns.1.running_var", "layer3.15.bns.2.weight", "layer3.15.bns.2.bias", "layer3.15.bns.2.running_mean", "layer3.15.bns.2.running_var", "layer3.16.convs.0.weight", "layer3.16.convs.1.weight", "layer3.16.convs.2.weight", "layer3.16.bns.0.weight", "layer3.16.bns.0.bias", "layer3.16.bns.0.running_mean", "layer3.16.bns.0.running_var", "layer3.16.bns.1.weight", "layer3.16.bns.1.bias", "layer3.16.bns.1.running_mean", "layer3.16.bns.1.running_var", "layer3.16.bns.2.weight", "layer3.16.bns.2.bias", "layer3.16.bns.2.running_mean", "layer3.16.bns.2.running_var", "layer3.17.convs.0.weight", "layer3.17.convs.1.weight", "layer3.17.convs.2.weight", "layer3.17.bns.0.weight", "layer3.17.bns.0.bias", "layer3.17.bns.0.running_mean", "layer3.17.bns.0.running_var", "layer3.17.bns.1.weight", "layer3.17.bns.1.bias", "layer3.17.bns.1.running_mean", "layer3.17.bns.1.running_var", "layer3.17.bns.2.weight", "layer3.17.bns.2.bias", "layer3.17.bns.2.running_mean", "layer3.17.bns.2.running_var", "layer3.18.convs.0.weight", "layer3.18.convs.1.weight", "layer3.18.convs.2.weight", "layer3.18.bns.0.weight", "layer3.18.bns.0.bias", "layer3.18.bns.0.running_mean", "layer3.18.bns.0.running_var", "layer3.18.bns.1.weight", "layer3.18.bns.1.bias", "layer3.18.bns.1.running_mean", "layer3.18.bns.1.running_var", "layer3.18.bns.2.weight", "layer3.18.bns.2.bias", "layer3.18.bns.2.running_mean", "layer3.18.bns.2.running_var", "layer3.19.convs.0.weight", "layer3.19.convs.1.weight", "layer3.19.convs.2.weight", "layer3.19.bns.0.weight", "layer3.19.bns.0.bias", "layer3.19.bns.0.running_mean", "layer3.19.bns.0.running_var", "layer3.19.bns.1.weight", "layer3.19.bns.1.bias", "layer3.19.bns.1.running_mean", "layer3.19.bns.1.running_var", "layer3.19.bns.2.weight", "layer3.19.bns.2.bias", "layer3.19.bns.2.running_mean", "layer3.19.bns.2.running_var", "layer3.20.convs.0.weight", "layer3.20.convs.1.weight", "layer3.20.convs.2.weight", "layer3.20.bns.0.weight", "layer3.20.bns.0.bias", "layer3.20.bns.0.running_mean", "layer3.20.bns.0.running_var", "layer3.20.bns.1.weight", "layer3.20.bns.1.bias", "layer3.20.bns.1.running_mean", "layer3.20.bns.1.running_var", "layer3.20.bns.2.weight", "layer3.20.bns.2.bias", "layer3.20.bns.2.running_mean", "layer3.20.bns.2.running_var", "layer3.21.convs.0.weight", "layer3.21.convs.1.weight", "layer3.21.convs.2.weight", "layer3.21.bns.0.weight", "layer3.21.bns.0.bias", "layer3.21.bns.0.running_mean", "layer3.21.bns.0.running_var", "layer3.21.bns.1.weight", "layer3.21.bns.1.bias", "layer3.21.bns.1.running_mean", "layer3.21.bns.1.running_var", "layer3.21.bns.2.weight", "layer3.21.bns.2.bias", "layer3.21.bns.2.running_mean", "layer3.21.bns.2.running_var", "layer3.22.convs.0.weight", "layer3.22.convs.1.weight", "layer3.22.convs.2.weight", "layer3.22.bns.0.weight", "layer3.22.bns.0.bias", "layer3.22.bns.0.running_mean", "layer3.22.bns.0.running_var", "layer3.22.bns.1.weight", "layer3.22.bns.1.bias", "layer3.22.bns.1.running_mean", "layer3.22.bns.1.running_var", "layer3.22.bns.2.weight", "layer3.22.bns.2.bias", "layer3.22.bns.2.running_mean", "layer3.22.bns.2.running_var", "layer4.0.convs.0.weight", "layer4.0.convs.1.weight", "layer4.0.convs.2.weight", "layer4.0.bns.0.weight", "layer4.0.bns.0.bias", "layer4.0.bns.0.running_mean", "layer4.0.bns.0.running_var", "layer4.0.bns.1.weight", "layer4.0.bns.1.bias", "layer4.0.bns.1.running_mean", "layer4.0.bns.1.running_var", "layer4.0.bns.2.weight", "layer4.0.bns.2.bias", "layer4.0.bns.2.running_mean", "layer4.0.bns.2.running_var", "layer4.1.convs.0.weight", "layer4.1.convs.1.weight", "layer4.1.convs.2.weight", "layer4.1.bns.0.weight", "layer4.1.bns.0.bias", "layer4.1.bns.0.running_mean", "layer4.1.bns.0.running_var", "layer4.1.bns.1.weight", "layer4.1.bns.1.bias", "layer4.1.bns.1.running_mean", "layer4.1.bns.1.running_var", "layer4.1.bns.2.weight", "layer4.1.bns.2.bias", "layer4.1.bns.2.running_mean", "layer4.1.bns.2.running_var", "layer4.2.convs.0.weight", "layer4.2.convs.1.weight", "layer4.2.convs.2.weight", "layer4.2.bns.0.weight", "layer4.2.bns.0.bias", "layer4.2.bns.0.running_mean", "layer4.2.bns.0.running_var", "layer4.2.bns.1.weight", "layer4.2.bns.1.bias", "layer4.2.bns.1.running_mean", "layer4.2.bns.1.running_var", "layer4.2.bns.2.weight", "layer4.2.bns.2.bias", "layer4.2.bns.2.running_mean", "layer4.2.bns.2.running_var".
Unexpected key(s) in state_dict: "layer1.0.conv2.weight", "layer1.0.bn2.running_mean", "layer1.0.bn2.running_var", "layer1.0.bn2.weight", "layer1.0.bn2.bias", "layer1.1.conv2.weight", "layer1.1.bn2.running_mean", "layer1.1.bn2.running_var", "layer1.1.bn2.weight", "layer1.1.bn2.bias", "layer1.2.conv2.weight", "layer1.2.bn2.running_mean", "layer1.2.bn2.running_var", "layer1.2.bn2.weight", "layer1.2.bn2.bias", "layer2.0.conv2.weight", "layer2.0.bn2.running_mean", "layer2.0.bn2.running_var", "layer2.0.bn2.weight", "layer2.0.bn2.bias", "layer2.1.conv2.weight", "layer2.1.bn2.running_mean", "layer2.1.bn2.running_var", "layer2.1.bn2.weight", "layer2.1.bn2.bias", "layer2.2.conv2.weight", "layer2.2.bn2.running_mean", "layer2.2.bn2.running_var", "layer2.2.bn2.weight", "layer2.2.bn2.bias", "layer2.3.conv2.weight", "layer2.3.bn2.running_mean", "layer2.3.bn2.running_var", "layer2.3.bn2.weight", "layer2.3.bn2.bias", "layer3.0.conv2.weight", "layer3.0.bn2.running_mean", "layer3.0.bn2.running_var", "layer3.0.bn2.weight", "layer3.0.bn2.bias", "layer3.1.conv2.weight", "layer3.1.bn2.running_mean", "layer3.1.bn2.running_var", "layer3.1.bn2.weight", "layer3.1.bn2.bias", "layer3.2.conv2.weight", "layer3.2.bn2.running_mean", "layer3.2.bn2.running_var", "layer3.2.bn2.weight", "layer3.2.bn2.bias", "layer3.3.conv2.weight", "layer3.3.bn2.running_mean", "layer3.3.bn2.running_var", "layer3.3.bn2.weight", "layer3.3.bn2.bias", "layer3.4.conv2.weight", "layer3.4.bn2.running_mean", "layer3.4.bn2.running_var", "layer3.4.bn2.weight", "layer3.4.bn2.bias", "layer3.5.conv2.weight", "layer3.5.bn2.running_mean", "layer3.5.bn2.running_var", "layer3.5.bn2.weight", "layer3.5.bn2.bias", "layer3.6.conv2.weight", "layer3.6.bn2.running_mean", "layer3.6.bn2.running_var", "layer3.6.bn2.weight", "layer3.6.bn2.bias", "layer3.7.conv2.weight", "layer3.7.bn2.running_mean", "layer3.7.bn2.running_var", "layer3.7.bn2.weight", "layer3.7.bn2.bias", "layer3.8.conv2.weight", "layer3.8.bn2.running_mean", "layer3.8.bn2.running_var", "layer3.8.bn2.weight", "layer3.8.bn2.bias", "layer3.9.conv2.weight", "layer3.9.bn2.running_mean", "layer3.9.bn2.running_var", "layer3.9.bn2.weight", "layer3.9.bn2.bias", "layer3.10.conv2.weight", "layer3.10.bn2.running_mean", "layer3.10.bn2.running_var", "layer3.10.bn2.weight", "layer3.10.bn2.bias", "layer3.11.conv2.weight", "layer3.11.bn2.running_mean", "layer3.11.bn2.running_var", "layer3.11.bn2.weight", "layer3.11.bn2.bias", "layer3.12.conv2.weight", "layer3.12.bn2.running_mean", "layer3.12.bn2.running_var", "layer3.12.bn2.weight", "layer3.12.bn2.bias", "layer3.13.conv2.weight", "layer3.13.bn2.running_mean", "layer3.13.bn2.running_var", "layer3.13.bn2.weight", "layer3.13.bn2.bias", "layer3.14.conv2.weight", "layer3.14.bn2.running_mean", "layer3.14.bn2.running_var", "layer3.14.bn2.weight", "layer3.14.bn2.bias", "layer3.15.conv2.weight", "layer3.15.bn2.running_mean", "layer3.15.bn2.running_var", "layer3.15.bn2.weight", "layer3.15.bn2.bias", "layer3.16.conv2.weight", "layer3.16.bn2.running_mean", "layer3.16.bn2.running_var", "layer3.16.bn2.weight", "layer3.16.bn2.bias", "layer3.17.conv2.weight", "layer3.17.bn2.running_mean", "layer3.17.bn2.running_var", "layer3.17.bn2.weight", "layer3.17.bn2.bias", "layer3.18.conv2.weight", "layer3.18.bn2.running_mean", "layer3.18.bn2.running_var", "layer3.18.bn2.weight", "layer3.18.bn2.bias", "layer3.19.conv2.weight", "layer3.19.bn2.running_mean", "layer3.19.bn2.running_var", "layer3.19.bn2.weight", "layer3.19.bn2.bias", "layer3.20.conv2.weight", "layer3.20.bn2.running_mean", "layer3.20.bn2.running_var", "layer3.20.bn2.weight", "layer3.20.bn2.bias", "layer3.21.conv2.weight", "layer3.21.bn2.running_mean", "layer3.21.bn2.running_var", "layer3.21.bn2.weight", "layer3.21.bn2.bias", "layer3.22.conv2.weight", "layer3.22.bn2.running_mean", "layer3.22.bn2.running_var", "layer3.22.bn2.weight", "layer3.22.bn2.bias", "layer4.0.conv2.weight", "layer4.0.bn2.running_mean", "layer4.0.bn2.running_var", "layer4.0.bn2.weight", "layer4.0.bn2.bias", "layer4.1.conv2.weight", "layer4.1.bn2.running_mean", "layer4.1.bn2.running_var", "layer4.1.bn2.weight", "layer4.1.bn2.bias", "layer4.2.conv2.weight", "layer4.2.bn2.running_mean", "layer4.2.bn2.running_var", "layer4.2.bn2.weight", "layer4.2.bn2.bias".
size mismatch for layer1.0.conv1.weight: copying a param with shape torch.Size([64, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([104, 64, 1, 1]).
size mismatch for layer1.0.bn1.weight: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([104]).
size mismatch for layer1.0.bn1.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([104]).
size mismatch for layer1.0.bn1.running_mean: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([104]).
size mismatch for layer1.0.bn1.running_var: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([104]).
size mismatch for layer1.0.conv3.weight: copying a param with shape torch.Size([256, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 104, 1, 1]).
size mismatch for layer1.1.conv1.weight: copying a param with shape torch.Size([64, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([104, 256, 1, 1]).
size mismatch for layer1.1.bn1.weight: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([104]).
size mismatch for layer1.1.bn1.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([104]).
size mismatch for layer1.1.bn1.running_mean: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([104]).
size mismatch for layer1.1.bn1.running_var: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([104]).
size mismatch for layer1.1.conv3.weight: copying a param with shape torch.Size([256, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 104, 1, 1]).
size mismatch for layer1.2.conv1.weight: copying a param with shape torch.Size([64, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([104, 256, 1, 1]).
size mismatch for layer1.2.bn1.weight: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([104]).
size mismatch for layer1.2.bn1.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([104]).
size mismatch for layer1.2.bn1.running_mean: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([104]).
size mismatch for layer1.2.bn1.running_var: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([104]).
size mismatch for layer1.2.conv3.weight: copying a param with shape torch.Size([256, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 104, 1, 1]).
size mismatch for layer2.0.conv1.weight: copying a param with shape torch.Size([128, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([208, 256, 1, 1]).
size mismatch for layer2.0.bn1.weight: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.0.bn1.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.0.bn1.running_mean: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.0.bn1.running_var: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.0.conv3.weight: copying a param with shape torch.Size([512, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([512, 208, 1, 1]).
size mismatch for layer2.1.conv1.weight: copying a param with shape torch.Size([128, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([208, 512, 1, 1]).
size mismatch for layer2.1.bn1.weight: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.1.bn1.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.1.bn1.running_mean: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.1.bn1.running_var: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.1.conv3.weight: copying a param with shape torch.Size([512, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([512, 208, 1, 1]).
size mismatch for layer2.2.conv1.weight: copying a param with shape torch.Size([128, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([208, 512, 1, 1]).
size mismatch for layer2.2.bn1.weight: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.2.bn1.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.2.bn1.running_mean: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.2.bn1.running_var: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.2.conv3.weight: copying a param with shape torch.Size([512, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([512, 208, 1, 1]).
size mismatch for layer2.3.conv1.weight: copying a param with shape torch.Size([128, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([208, 512, 1, 1]).
size mismatch for layer2.3.bn1.weight: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.3.bn1.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.3.bn1.running_mean: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.3.bn1.running_var: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([208]).
size mismatch for layer2.3.conv3.weight: copying a param with shape torch.Size([512, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([512, 208, 1, 1]).
size mismatch for layer3.0.conv1.weight: copying a param with shape torch.Size([256, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 512, 1, 1]).
size mismatch for layer3.0.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.0.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.0.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.0.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.0.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.1.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.1.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.1.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.1.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.1.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.1.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.2.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.2.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.2.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.2.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.2.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.2.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.3.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.3.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.3.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.3.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.3.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.3.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.4.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.4.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.4.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.4.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.4.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.4.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.5.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.5.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.5.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.5.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.5.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.5.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.6.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.6.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.6.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.6.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.6.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.6.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.7.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.7.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.7.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.7.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.7.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.7.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.8.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.8.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.8.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.8.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.8.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.8.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.9.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.9.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.9.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.9.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.9.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.9.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.10.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.10.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.10.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.10.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.10.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.10.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.11.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.11.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.11.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.11.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.11.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.11.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.12.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.12.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.12.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.12.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.12.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.12.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.13.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.13.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.13.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.13.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.13.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.13.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.14.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.14.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.14.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.14.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.14.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.14.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.15.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.15.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.15.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.15.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.15.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.15.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.16.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.16.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.16.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.16.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.16.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.16.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.17.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.17.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.17.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.17.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.17.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.17.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.18.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.18.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.18.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.18.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.18.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.18.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.19.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.19.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.19.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.19.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.19.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.19.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.20.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.20.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.20.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.20.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.20.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.20.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.21.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.21.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.21.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.21.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.21.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.21.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer3.22.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([416, 1024, 1, 1]).
size mismatch for layer3.22.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.22.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.22.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.22.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([416]).
size mismatch for layer3.22.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 416, 1, 1]).
size mismatch for layer4.0.conv1.weight: copying a param with shape torch.Size([512, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([832, 1024, 1, 1]).
size mismatch for layer4.0.bn1.weight: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([832]).
size mismatch for layer4.0.bn1.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([832]).
size mismatch for layer4.0.bn1.running_mean: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([832]).
size mismatch for layer4.0.bn1.running_var: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([832]).
size mismatch for layer4.0.conv3.weight: copying a param with shape torch.Size([2048, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([2048, 832, 1, 1]).
size mismatch for layer4.1.conv1.weight: copying a param with shape torch.Size([512, 2048, 1, 1]) from checkpoint, the shape in current model is torch.Size([832, 2048, 1, 1]).
size mismatch for layer4.1.bn1.weight: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([832]).
size mismatch for layer4.1.bn1.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([832]).
size mismatch for layer4.1.bn1.running_mean: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([832]).
size mismatch for layer4.1.bn1.running_var: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([832]).
size mismatch for layer4.1.conv3.weight: copying a param with shape torch.Size([2048, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([2048, 832, 1, 1]).
size mismatch for layer4.2.conv1.weight: copying a param with shape torch.Size([512, 2048, 1, 1]) from checkpoint, the shape in current model is torch.Size([832, 2048, 1, 1]).
size mismatch for layer4.2.bn1.weight: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([832]).
size mismatch for layer4.2.bn1.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([832]).
size mismatch for layer4.2.bn1.running_mean: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([832]).
size mismatch for layer4.2.bn1.running_var: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([832]).
size mismatch for layer4.2.conv3.weight: #copying a param with shape torch.Size([2048, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([2048, 832, 1, 1]).

hi . i have the same issue,canyou reslove it?

Please make sure that you use the Res2Net instead of ResNet.
Provide me with the code to reproduce this error can help to solve this problem.

@gasvn
Copy link
Member

gasvn commented Mar 9, 2020

i have the same problem.but i have solve it. you don't change the .yaml file.one word,it work.
i add TEST_PERIOD: 10000 model.it don't work.I am thinking the problem.if you solve ,please contact me.

I am confused. We don't have any yaml file in this repo.

@RLiBIn
Copy link

RLiBIn commented Mar 9, 2020

https://github.com/Res2Net/Res2Net-maskrcnn/blob/master/configs/pytorch_mask_rcnn_R2_50_s4_FPN_2x.yaml

@gasvn
Copy link
Member

gasvn commented Mar 9, 2020

https://github.com/Res2Net/Res2Net-maskrcnn/blob/master/configs/pytorch_mask_rcnn_R2_50_s4_FPN_2x.yaml

That is the res2net-maskrcnn repo. What do you mean "i add TEST_PERIOD: 10000 model.it don't work"? I don't quite understand your problem.
You can contact me with email in Chinese if you like.

@RLiBIn
Copy link

RLiBIn commented Mar 9, 2020

我最终发现是犯了很愚蠢的错误
MODEL:
META_ARCHITECTURE: "GeneralizedRCNN"
WEIGHT: "/root/data/res2net50_26w_4s-06e79181.pth"
BACKBONE:
CONV_BODY: "R2-50-FPN"
RESNETS:
BACKBONE_OUT_CHANNELS: 256
WIDTH_PER_GROUP: 26
SCALE: 8
TRANS_FUNC: "Bottle2neckWithFixedBatchNorm"

其中width，scale要与res2net50_26w_4s-06e79181.pth保持一致。
但是在测试res2net50_v1b_26w_4s-3cf99910.pth 并更改width，scale时，会发生错误
Traceback (most recent call last):
File "tools/train_net.py", line 178, in
main()
File "tools/train_net.py", line 171, in main
model = train(cfg, args.local_rank, args.distributed)
File "tools/train_net.py", line 56, in train
extra_checkpoint_data = checkpointer.load(cfg.MODEL.WEIGHT)
File "/root/data/Res2Net-maskrcnn/maskrcnn_benchmark/utils/checkpoint.py", line 62, in load
self._load_model(checkpoint)
File "/root/data/Res2Net-maskrcnn/maskrcnn_benchmark/utils/checkpoint.py", line 98, in _load_model
load_state_dict(self.model, checkpoint.pop("model"))
File "/root/data/Res2Net-maskrcnn/maskrcnn_benchmark/utils/model_serialization.py", line 80, in load_state_dict
model.load_state_dict(model_state_dict)
File "/root/anaconda3/envs/maskrcnn/lib/python3.7/site-packages/torch/nn/modules/module.py", line 769, in load_state_dict
self.class.name, "\n\t".join(error_msgs)))
RuntimeError: Error(s) in loading state_dict for GeneralizedRCNN:
size mismatch for backbone.body.layer1.0.downsample.1.weight: copying a param with shape torch.Size([256, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for backbone.body.layer2.0.downsample.1.weight: copying a param with shape torch.Size([512, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([512]).
size mismatch for backbone.body.layer3.0.downsample.1.weight: copying a param with shape torch.Size([1024, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for backbone.body.layer4.0.downsample.1.weight: copying a param with shape torch.Size([2048, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([2048]).

@Taylor-X76 Taylor-X76 mentioned this issue Apr 17, 2020
Closed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
4 participants
@vatsalag99 @gasvn @mathpopo @RLiBIn