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

Self-discovery autoencoder training approach #3

Open
tomwlod opened this issue Apr 12, 2021 · 0 comments
Open

Self-discovery autoencoder training approach #3

tomwlod opened this issue Apr 12, 2021 · 0 comments

Comments

@tomwlod
Copy link

tomwlod commented Apr 12, 2021

Hello

According to what you wrote in https://arxiv.org/pdf/2007.06959.pdf, use a trained autoencoder to obtain deep latent features. However, I found in https://github.com/fhaghighi/SemanticGenesis/blob/master/self_discovery/train_autoencoder.py that you used Unet3D as a mentioned autoencoder. How did you train it? As you know every Unet has skip connections that prevent the autoencoder to generalize at all. Am I missing something here?

Tom

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