Vision Transformer

An Implemenentation of the paper An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale in Pytorch.

Installation

• Clone the repository

git clone https://github.com/dakofler/vision_transformer.git
cd vision_transformer/

• (Optional) Create a Python virtual environment (Linux)

python3 -m venv .venv
source .venv/bin/activate

• Install dependencies

pip install -r requirements.txt

Usage

• Download the CIFAR10-10 dataset
• Upack and put the files into a ./data directory

vision_transformer/
├─ data/
│  ├─ batches.meta
│  ├─ data_batch_1
│  ├─ data_batch_2
│  ├─ data_batch_3
│  ├─ data_batch_4
│  ├─ data_batch_5
│  ├─ readme.html
│  ├─ test_batch
...

• run the training script

python3 train.py

Author

Daniel Kofler - dkofler@outlook.com
2025