all-things-vits/code-samples
Holds code for our CVPR'23 tutorial: All Things ViTs: Understanding and Interpreting Attention in Vision.
This project provides practical code samples and notebooks to understand how Vision Transformers (ViTs) make decisions when classifying images. You input an image and a trained ViT model, and it outputs visual explanations showing which parts of the image the model focused on. This is for researchers and practitioners working with computer vision models, particularly those using attention-based architectures.
197 stars. No commits in the last 6 months.
Use this if you need to interpret why a Vision Transformer made a specific prediction on an image.
Not ideal if you are looking for a general-purpose image classification library or tools for traditional computer vision tasks.
Stars
197
Forks
12
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Jun 20, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/all-things-vits/code-samples"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
jaehyunnn/ViTPose_pytorch
An unofficial implementation of ViTPose [Y. Xu et al., 2022]
UdbhavPrasad072300/Transformer-Implementations
Library - Vanilla, ViT, DeiT, BERT, GPT
tintn/vision-transformer-from-scratch
A Simplified PyTorch Implementation of Vision Transformer (ViT)
icon-lab/ResViT
Official Implementation of ResViT: Residual Vision Transformers for Multi-modal Medical Image Synthesis
gupta-abhay/pytorch-vit
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale