Reproduction of Vision Transformer based on this amazing blog post
- Implement Dense Prediction Structure
Install dependencies
# clone project
git clone https://github.com/gsoykan/ViT-PyTorch-implementation
ViT-PyTorch-implementation
# [OPTIONAL] create conda environment
conda create -n myenv python=3.8
conda activate myenv
# install pytorch according to instructions
# https://pytorch.org/get-started/
# install requirements
pip install -r requirements.txt
Train model with default configuration
# train on CPU
python run.py trainer.gpus=0
# train on GPU
python run.py trainer.gpus=1
Train model with chosen experiment configuration from configs/experiment/
python run.py experiment=experiment_name.yaml
You can override any parameter from command line like this
python run.py trainer.max_epochs=20 datamodule.batch_size=64