search

BiomedSciAI / fuse-med-ml

A python framework accelerating ML based discovery in the medical field by encouraging code reuse. Batteries included :)
Apache License 2.0
134 stars 34 forks source link

Transformer + 1D/2D/3D Vision Transformer #200

Closed avihu111 closed 1 year ago

mosheraboh commented 1 year ago

The jenkinks tests fail in all PRs. Sagi and I looking for a solution. You can ignore it for now.

egozi commented 1 year ago

I want to add a few things:

  1. default parameters for depth, heads etc.
  2. standard models like - vit_base, vit_large, …
  3. the interpolation module for diff image sizes.
  4. What about pre trained weights? and an option flag.
SagiPolaczek commented 1 year ago

@egozi Hey Amir :) Sounds cool.

Could you please open an issue on those suggestions? While its best to open with our templates, there is a quicker way to do so: In the comment's menu click "Reference in a new issue".