To boost baseline model construction and incremental hypothesis testing speed.
You can use this library for both machine learning and deep learning tasks only with changing some argments.
- cuda >= 10.0
To use the image with a GPU you'll need to have nvidia-docker installed.
sudo docker run -ti --gpus all -v `pwd`/data:/workspace/data -p 8888:8888 --net=host --ipc=host pelada/ml_pkg:latest # Enters with /bin/bash, mounting the /data drive in the container
conda create -n ml_dl_pkg python=3.7
source activate ml_dl_pkg
Only for mac user, Please install xgboost from source
https://xgboost.readthedocs.io/en/latest/build.html#building-on-osx
ref: https://github.com/NVIDIA/apex
cd ../
git clone https://github.com/NVIDIA/apex;cd apex
pip install -v --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" ./
cd ../ml_dl_pkg
For CPU users,
mkdir -p apex/amp
Lastly,
pip install -r requirements.txt
python setup.py install
mkdir input/eeg;unzip 'input/*.zip' -d input/eeg/;
python example.py --transform spectrogram