https://github.com/xaxm007/vit-pytorch

Paper replication of Vision Transformer (ViT) research paper and fine-tuning on custom dataset
https://github.com/xaxm007/vit-pytorch

fine paper-repl pytorch scratch-implementation vision

Last synced: 7 months ago
JSON representation

Paper replication of Vision Transformer (ViT) research paper and fine-tuning on custom dataset

• Host: GitHub
• URL: https://github.com/xaxm007/vit-pytorch
• Owner: xaxm007
• Created: 2025-03-18T14:46:32.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2025-06-14T04:22:43.000Z (10 months ago)
• Last Synced: 2025-06-24T00:03:19.238Z (10 months ago)
• Topics: fine, paper-repl, pytorch, scratch-implementation, vision
• Language: Jupyter Notebook
• Homepage:
• Size: 1.6 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# ViT-PyTorch

Understanding Vision Transformer by implementation using PyTorch.

| ![ViT](./images/vit_architecture.png) |

|:--------------------------------:|

### [scratch_ViT](./scratch_ViT.ipynb):

* Building Vision Transformer from scratch and training on MNIST dataset.

### [paper_replication](./paper_replication.ipynb):

* Replicating Vision Transformer (ViT) Research Paper using PyTorch.

* Fine-tuning pretrained ViT on custom dataset.