bwconrad/vit-finetune
Fine-tuning Vision Transformers on various classification datasets
This project helps machine learning practitioners adapt powerful image recognition models (Vision Transformers) to their specific image classification needs. You provide a collection of images organized into folders for different categories, and it outputs a highly accurate model capable of classifying new images into those categories. This is ideal for AI/ML engineers, data scientists, and researchers building custom image classification solutions.
115 stars. No commits in the last 6 months.
Use this if you need to build a high-performing image classification model for your unique dataset without training one from scratch, leveraging state-of-the-art Vision Transformers.
Not ideal if you're not comfortable working with command-line tools and machine learning frameworks, or if you need a simple out-of-the-box solution without any customization.
Stars
115
Forks
22
Language
Python
License
MIT
Category
Last pushed
Aug 31, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/bwconrad/vit-finetune"
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.
zhanghang1989/ResNeSt
ResNeSt: Split-Attention Networks
berniwal/swin-transformer-pytorch
Implementation of the Swin Transformer in PyTorch.
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...