EthanBnntt/tinygrad-vit
A minimalist implementation of the ViT (Vision Transformer) model, using tinygrad
This project helps machine learning practitioners or researchers who want to understand or experiment with the core mechanics of Vision Transformers (ViT) for image classification. It takes images as input and processes them to classify what's in the image, demonstrating how a transformer architecture can be applied to visual data without complex convolutional layers. It's designed for those familiar with deep learning concepts but seeking a stripped-down, readable implementation.
No commits in the last 6 months.
Use this if you are an ML practitioner or student interested in a barebones, educational implementation of a Vision Transformer to understand its internal workings for image classification.
Not ideal if you need a production-ready, highly optimized, or feature-rich Vision Transformer for immediate deployment or large-scale tasks.
Stars
15
Forks
1
Language
Python
License
MIT
Category
Last pushed
Sep 02, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/EthanBnntt/tinygrad-vit"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Jittor/jittor
Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.
berniwal/swin-transformer-pytorch
Implementation of the Swin Transformer in PyTorch.
zhanghang1989/ResNeSt
ResNeSt: Split-Attention Networks
NVlabs/FasterViT
[ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with...
ViTAE-Transformer/ViTPose
The official repo for [NeurIPS'22] "ViTPose: Simple Vision Transformer Baselines for Human Pose...