BobMcDear/vit-pytorch

PyTorch implementation of the vision transformer

22
/ 100
Experimental

This project helps machine learning engineers or researchers implement a Vision Transformer (ViT) architecture in PyTorch. It takes raw image data as input and outputs classifications based on the visual content. The end-user is a deep learning practitioner working on computer vision tasks.

No commits in the last 6 months.

Use this if you are a machine learning engineer or researcher building custom computer vision models and need a flexible, modular PyTorch implementation of the Vision Transformer.

Not ideal if you are looking for a pre-trained model or a high-level API for immediate image classification without diving into model architecture details.

computer-vision deep-learning image-classification neural-networks model-building
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

17

Forks

Language

Python

License

GPL-3.0

Last pushed

Mar 30, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/BobMcDear/vit-pytorch"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.