-
Notifications
You must be signed in to change notification settings - Fork 30
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
Do video models dream of electrical sheeps in motion #19
Conversation
Here's where we are right now:
Here are example videos maximizing layer3 and layer4 activations: Learnings
We then looked into regularization terms to get rid of the high-frequency patterns; the total variation regularization loss implemented right now results in very strong checkerboard patterns. Next actions: figure out better regularization term and look into prior art how other folks handle this. |
Dayum 🔥 |
Bringing back the 3d total variation loss term and scaling it seems to get rid of high frequencies in the output which makes it more pleasant to look at 🤗 direct comparison: |
2cb8bfa
to
7634e4b
Compare
Merging this into master as is right now. We can explore more advanced techniques such as dreaming at multiple scales and related in separate pull requests in the future. |
Work in progress; let's see if this works out 🤗