Skip to content

v1.0.5 - Finetuning Improvements, Max-ViT
Compare
Choose a tag to compare
@mwalmsley mwalmsley released this 13 Nov 20:15
· 331 commits to main since this release
v1.0.5
3214941
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Learn about vigilant mode.

What's Changed

Major improvements to finetuning.

  • Now supports finetuning resnet and maxvit-tiny! This previously only worked as static pretrained models.
  • Now specify num_blocks instead of num_layers, reflecting the network structure (effnet, resnet50, maxvit)
  • Now you can 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

Full Changelog: v1.0.4...v1.0.5

Assets 2