VAE notebooks (copilot-generated) #10
Draft
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Overall, I think the notebooks can be a good starting point. Our VAE implementation has a comparable structure (and is also based on other notebooks/implementations). Of course, there some details one should check (e.g. the last sigmoid layer of the decoder, which can work fine with BCE Loss and MinMax scaled input, but not with other stuff) + some nicer visualizations and figures. Especially the latent space should colored by the digit class. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR adds some notebooks about Variational Auto-Encoders.
These notebooks are AI-generated (using github copilot workspace + gpt4omni). I just ran them in this environment and they worked just fine. I'm now wondering if these are useful, a potential starting point for modifications of if we should start from scratch.
@jan-forest and @MaxJoas would you mind taking a look and letting me know what you think?
Big thanks!
closes #1