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

Three changes compared to keras version v1 #14

Closed

rainsun1 opened this issue Sep 28, 2019 · 1 comment

rainsun1 commented Sep 28, 2019

I noticed 3 insteresting changes in this version compared to v1:

"compositional_loss" and "overall_loss" are removed, and only "alpha_prediction_loss" remains.
"model refinement" step with dense layers or "torch.nn.linear" are removed, and only "encorder and decoder" layers remains.
So, maybe this is a light version of v1.
"generate_trimap(alpha)" function changes a lot, which can generate much large and usual unknown region size and is perhaps a key point for the improvement of the results.

Owner

foamliu commented Oct 11, 2019

Thanks for the good summary.

foamliu closed this as completed

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment