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

Finetuning improvements #110

Merged
merged 16 commits into from
Nov 13, 2023
Merged

Finetuning improvements #110

merged 16 commits into from
Nov 13, 2023

Conversation

mwalmsley
Copy link
Owner

@mwalmsley mwalmsley commented Nov 9, 2023

Major improvements to finetuning.

  • Now supports resnet and maxvit-tiny!
  • Now specify num_blocks instead of num_layers.
  • Optionally keep batchnorm layers always trainable

Small changes:
Update dependency to use galaxy-datasets==0.15.0
Replace multi-class example with new galaxy-mnist dataset
Fixes #108

The next release will update timm to 0.9ish
Pytorch 2.1.0 already works, and the next release will also reflect that

@mwalmsley mwalmsley merged commit 3214941 into main Nov 13, 2023
4 checks passed
@mwalmsley mwalmsley mentioned this pull request Nov 13, 2023
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.

Subtle error in predict_on_catalog due to large default batch_size
1 participant