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

how to freeze backbone in oscd #6

Open
MGLiXu opened this issue Oct 17, 2021 · 2 comments
Open

how to freeze backbone in oscd #6

MGLiXu opened this issue Oct 17, 2021 · 2 comments

Comments

@MGLiXu
Copy link

MGLiXu commented Oct 17, 2021

Hi,
I can't find how you freeze backbone in oscd task, maybe in main_oscd.py or segmentation.py but i can't find the code(such as torch.no_grad?). Could you please tell me where is it.
Thanks.

@nostalgiaa-a
Copy link

Hi, I can't find how you freeze backbone in oscd task, maybe in main_oscd.py or segmentation.py but i can't find the code(such as torch.no_grad?). Could you please tell me where is it. Thanks.

Do you know how to freeze weights yet?

@joshmyersdean
Copy link

It looks like they only pass through the parameters after the encoder to the optimizer.

        params = set(self.model.parameters()).difference(self.model.encoder.parameters())

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

3 participants