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 do you train deeplab v2 with full supervised method using your pseudo label? #5

Open
TyroneLi opened this issue Sep 29, 2020 · 3 comments

Comments

@TyroneLi
Copy link

DO you change any parameters or model architecture using this repro?

@zerodohero
Copy link

I'd like to know

@wasidennis
Copy link

@TyroneLi @zerodohero The model architecture is the same. We did not heavily tune the model but just lower the learning rate a bit to account for noisy pseudo labels.

@kkechen
Copy link

kkechen commented Dec 16, 2020

Sorry to bother you, @wasidennis could you share the modified parameter e.g. learning rate of the segmentation network. That would be helpful for us to re-implement your work, thanks

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

4 participants