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

Pretrained models doesn't match code #7

Open
dreminm opened this issue Dec 22, 2021 · 2 comments
Open

Pretrained models doesn't match code #7

dreminm opened this issue Dec 22, 2021 · 2 comments

Comments

@dreminm
Copy link

dreminm commented Dec 22, 2021

Hi! Greatly appreciate your work! It seems that pretrained weights that you provided in issue #1 doesn't match the code:

  • layers are named differently
  • there is size mismatch in some layers, f.e. size mismatch for layer3.3.conv2.ffc.convl2l.weight: copying a param with shape torch.Size([192, 192, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 128, 3, 3]).

Can you please check it out?

@VuHuy-cse-9
Copy link

Hi!
I fix it with this code:
image
I hope it can help you.

@VuHuy-cse-9
Copy link

In my case, the name of ckpt layers don't matched with that from model, I fix it with this code:
image

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

2 participants