Building Vision models in Keras3 for framework-agnostic training and inference.
Project description
Porting all models from everywhere to Keras to leverage multi-backend support.
Cause why not?🤷🏻♂️
Installation:
-
Option 1: Install from PyPI:
pip install -U keras-vision -
Option 2: Install the latest updates present in the repository:
pip install git+https://github.com/veb-101/keras-vision.git
Usage: Please refer to the examples folder
Updates
- [2024-05-04] Converted MobileViT to Keras 3 and released weights of all 3 variants.
- Jax backend currently not working, I'm working on a fix.
- Release: https://github.com/veb-101/keras-vision/releases/tag/v0.4
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
keras_vision-0.4.5.tar.gz
(10.0 kB
view hashes)
Built Distribution
Close
Hashes for keras_vision-0.4.5-py3-none-any.whl
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | d391bdd14bd88fa34783ac14bae350cb82873cc6d833c33bc82a88097e78c3ef |
|
| MD5 | 16e5b7ed4d1db6a50cccd2a0d95707d6 |
|
| BLAKE2b-256 | 6e1ca381a2adb5808db27812298c529910bd89c32aafbbccf95a367f2e788cc6 |
