Skip to content

Instantly share code, notes, and snippets.

@fgolemo

fgolemo/autobots_omniglot.ipynb

Created March 1, 2022 22:26
Show Gist options
  • Save fgolemo/45583727ca7ba763b8656e97ba14da76 to your computer and use it in GitHub Desktop.
Save fgolemo/45583727ca7ba763b8656e97ba14da76 to your computer and use it in GitHub Desktop.
Download ZIP
Omniglot example for Autobots: Latent Variable Sequential Set Transformers
Display the source blob
Display the rendered blob
Raw
autobots_omniglot.ipynb
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@xuqingyao
Copy link

Hello, thank you for your amazing work of Autobot architecture. I tried this code in my server but I found the code run very slowly on gpu(about 800+ min per epoch), especially the calculation of MultivariateNormal in the loss part(one need at least half a minute). I wonder if this is some version problems since my torch version is 1.8.0 and torchvision version is 0.9.0. Thank you again for your attention.

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