tinygrad Image Models
Project description
tinygrad Image Models
A collection of vision models implemented in tinygrad, in a similar vein to timm.
Mostly targeting models trained on Imagenet-1k, and other models that are fast on resource-constrained devices.
Models
- ShuffleNetV2 - paper code
- GhostNetV2 - paper code
- FocalNet - paper code
- FastViT - paper code
- RepViT - paper code
TODO
- For models that can be reparameterized, add that functionality
- Training
License
See LICENSE.
Certain parts of the code are adapted from the original implementations, but they should all be under permissive licenses.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
tgim-0.0.0.tar.gz
(13.3 kB
view hashes)
Built Distribution
tgim-0.0.0-py3-none-any.whl
(17.4 kB
view hashes)