Skip to main content

UniGaze Easy Loader

A tiny, dependency-light Python package to load UniGaze pretrained models from Hugging Face.

📦 Installation

Install a matching PyTorch first.

pip install torch==2.0.1 torchvision==0.15.2 --index-url https://download.pytorch.org/whl/cu118
pip install timm==0.3.2
pip install unigaze

🚀 Quick Start

import torch
model = unigaze.load("unigaze_h14_joint", device="cuda")   # downloads weights from HF on first use
# Input: normalized batch (B, 3, 224, 224)
image_normalized_batch = torch.ones((10, 3, 224, 224), device="cuda")
# Output: {'pred_gaze': (B, 2)} with (pitch, yaw)
pred_gaze = model(image_normalized_batch)['pred_gaze']
print(pred_gaze.shape)  # torch.Size([10, 2])

Release files for unigaze 0.1.3

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for unigaze 0.1.3
File Size Uploaded
unigaze-0.1.3.tar.gz 16.9 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for unigaze 0.1.3
File Interpreter ABI Platform
unigaze-0.1.3-py3-none-any.whl Python 3 none any Details

Total release size: 33.4 kB

Release files / unigaze-0.1.3.tar.gz

Download URL unigaze-0.1.3.tar.gz
Size 16.9 kB
Tags Source
SHA-256 checksum
How to use checksums
886c1bcbed1f22bfa66a23761e218dab7c443e4fe31a3fa2b752e31bc29dc0db
BLAKE2b-256 checksum
How to use checksums
1747861770d6ac8628d96aae41f91cdce7380d1297efc9a4d90bbb426afb73cf
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.9.25

Release files / unigaze-0.1.3-py3-none-any.whl

Download URL unigaze-0.1.3-py3-none-any.whl
Size 16.4 kB
Tags Python 3
SHA-256 checksum
How to use checksums
a3f4101ac105d56f0e23e7ee9bd1981304c43b6677073231fd6140e184aefa7d
BLAKE2b-256 checksum
How to use checksums
dc453f18355876d7a6f1b14e01481657aa3921db3e703f19aaa290f6d92e99f0
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.9.25

Release history Release notifications | RSS feed

This release

0.1.3 This release

2 release files

0.1.2

2 release files

0.1.1

2 release files

0.1.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page