Kaimaoge / simple-vit

Simple implementation of Vision Transformer

SimpleViT

Simple implementation of Vision Transformer for Image Classification.

• DRL framework : PyTorch

Install

git clone https://github.com/isk03276/SimpleViT
cd SimpleViT
pip install -r requirements.txt

Getting Started

python main.py --dataset-name DATASET_NAME(ex. cifar10) --device DEVICE(ex. cuda, cpu) #train
python main.py --dataset-name DATASET_NAME(ex. cifar10) --device DEVICE(ex. cuda, cpu) --load-from MODEL_PATH --load-model-config #test

Results

- CIFAR-10

- CIFAR-100