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.

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

Which folder should I put the pretrained model dml_str_lapa.pth in? #2620

Open
king1111sadjfoisja opened this issue Jul 26, 2024 · 1 comment

Comments

@king1111sadjfoisja
Copy link

Dear Author:
Thank you for open-source such a great work!
When testing pretrained models,I encountered the following problems:
After downloading dml_csr_lapa.pth,I have no idea which folder in my project to put in,so I creat a folder named snapshots and ran the folowing command:

python test.py --data-dir ./dataset/NeRSemble/ --out-dir ./output/ --restore-from ./snapshots/dml_csr_lapa.pth --gpu 0 --batch-size 7 --input-size 473,473 --dataset test --n
um-classes 19

Program error:

RuntimeError: Error(s) in loading state_dict for DML_CSR:
        size mismatch for layer6.conv4.weight: copying a param with shape torch.Size([11, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([19, 256, 1, 1]).
        size mismatch for layer6.conv4.bias: copying a param with shape torch.Size([11]) from checkpoint, the shape in current model is torch.Size([19]).

image
This demonstrates the folder information within my project.

@king1111sadjfoisja
Copy link
Author

I d like to know how I can fix this problem and how to test pretrained model(which folder should i put dml_csr_lapa.pth in ?)
Thanks a lot!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant