Skip to content

VAE notebooks (copilot-generated)#10

Draft
haesleinhuepf wants to merge 4 commits into
mainfrom
vae
Draft

VAE notebooks (copilot-generated)#10
haesleinhuepf wants to merge 4 commits into
mainfrom
vae

Conversation

@haesleinhuepf

@haesleinhuepf haesleinhuepf commented Aug 12, 2024

Copy link
Copy Markdown
Member

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

@jan-forest

Copy link
Copy Markdown
Member

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.
But, yeah, it looks usable to start with a tutorial on VAE's.

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

Successfully merging this pull request may close these issues.

Variational Auto Encoders (VAE)

2 participants