This is the supplementary repository for the tutorial
Build and Train Vision Transformer from Scratch
After you've cloned the repository, you need to install required packages.
Run the following command to install packages:
pip install -r requirements.txt
Install PyTorch libraries with the command from official web-site:
pip install torch torchvision --index-url https://download.pytorch.org/whl/cu118
Then install the rest of the libraries with the command:
pip install -r requirements-cuda.txt