BCI-ToolBox is deep learning pipeline for motor-imagery classification.
This repo contains five models: ShallowConvNet, DeepConvNet, EEGNet, FBCNet, BCI2021.
(BCI2021 is not an official name.)
- Python == 3.7.10
- PyTorch == 1.9.0
- mne == 0.23.0
- braindecode == 0.5.1
- CUDA == 11.0
conda install pytorch=1.9.0 cudatoolkit=11.1 -c pytorch -c nvidia
conda install numpy pandas matplotlib pyyaml ipywidgets
pip install torchinfo braindecode moabb mne.
├── README.md
├── base
│ ├── constructor.py
│ └── layers.py
├── configs
│ ├── BCI2021
│ │ └── default.yaml
│ ├── DeepConvNet
│ │ └── default.yaml
│ ├── EEGNet
│ │ └── default.yaml
│ ├── FBCNet
│ │ └── default.yaml
│ ├── ShallowConvNet
│ │ └── default.yaml
│ └── demo
│ ├── arch.yaml
│ ├── bci2021.yaml
│ ├── test.yaml
│ ├── train.yaml
│ └── training_params.yaml
├── data_loader
│ ├── data_generator.py
│ ├── datasets
│ │ ├── __init__.py
│ │ ├── bnci2014.py
│ │ ├── cho2017.py
│ │ ├── folder_dataset.py
│ │ ├── openbmi.py
│ │ └── tmp_dataset.py
│ └── transforms.py
├── main.py
├── models
│ ├── BCI2021
│ │ ├── BCI2021.py
│ │ └── __init__.py
│ ├── DeepConvNet
│ │ ├── DeepConvNet.py
│ │ └── __init__.py
│ ├── EEGNet
│ │ ├── EEGNet.py
│ │ └── __init__.py
│ ├── FBCNet
│ │ ├── FBCNet.py
│ │ └── __init__.py
│ ├── ShallowConvNet
│ │ ├── ShallowConvNet.py
│ │ └── __init__.py
│ ├── __init__.py
│ └── model_builder.py
├── trainers
│ ├── __init__.py
│ ├── cls_trainer.py
│ └── trainer_maker.py
└── utils
├── calculator.py
├── painter.py
└── utils.py
- Use braindecode
- We use W&B for experimental management tool.
- Example for W&B Dashboard
- Example for W&B Report
- Create wandb_key.yaml file in configs directory.
# wandb_key.yaml key: WANDB API keys
- WANDB API keys can be obtained from your W&B account settings.
Use W&B
python main.py --config_file=configs/demo/train.yamlNot use W&B
python main.py --config_file=configs/demo/train.yaml --no_wandbUSE GPU
python main.py --config_file=configs/demo/train.yaml --device=0 # Use GPU 0
python main.py --config_file=configs/demo/train.yaml --device=1 # Use GPU 1
python main.py --config_file=configs/demo/train.yaml --device=2 # Use GPU 2- GPU numbers depend on your server.
USE Sweep
# W&B
sweep_file: configs/demo/training_params.yaml
project: Demo
tags: [train]- Add this block to config file for finding training parameters.
# W&B
sweep_file: configs/demo/arch.yaml
sweep_type: arch
project: Demo
tags: [train]- Add this block to config file for finding model architecture.
python main.py --config_file=configs/demo/test.yaml
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent