UniGaze: lightweight loader that pulls pretrained weights from Hugging Face
Reason this release was yanked:
package version is not compatible
Project description
UniGaze Easy Loader
A tiny, dependency-light Python package to load UniGaze pretrained models from the Hugging Face Hub.
One-liner:
import unigaze as ug
model = ug.load("unigaze_h14_joint", device="cuda") # auto-downloads from HF on first use
📦 Installation
This package does not install PyTorch for you. Install a matching PyTorch first.
CPU example
## E.g., CUDA 12.8
pip install torch==2.7.0 torchvision==0.22.0 --index-url https://download.pytorch.org/whl/cu128
pip install unigaze
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
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file unigaze-0.1.0.tar.gz.
File metadata
- Download URL: unigaze-0.1.0.tar.gz
- Upload date:
- Size: 16.3 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.9.25
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
5fbaf5690357b9a257f37b3c8df734a6dbb72976eb37c46d2dba25f1f0edb014
|
|
| MD5 |
603658ba8b3e7df11aa89ee0d391ae7b
|
|
| BLAKE2b-256 |
d395a40c5931ba8ee905947b35998c0439973c07b85c064f4ccaed066339143a
|
File details
Details for the file unigaze-0.1.0-py3-none-any.whl.
File metadata
- Download URL: unigaze-0.1.0-py3-none-any.whl
- Upload date:
- Size: 15.9 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.9.25
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
a582033d91c93874b2d5a2b4abdec266bb76761e514b063599d7b8c090c1b2cf
|
|
| MD5 |
d627f913f88dd4b7e0bf3b689fa75ec8
|
|
| BLAKE2b-256 |
1e635d247a55c1a9a0bde4dcfcdea92c1e202e3ea4c4948dfcd5df85d9b3ff61
|
