- Python 3.7+
- Julia 1.7+
- If you use docker gpu, you should install
nvidia-cuda-toolkit
andnvidia-container-toolkit
sudo apt install -y nvidia-cuda-toolkit # nvidia-cuda-toolkit installation
distribution=$(. /etc/os-release;echo $ID$VERSION_ID)
curl -s -L https://nvidia.github.io/nvidia-docker/gpgkey | sudo apt-key add -
curl -s -L https://nvidia.github.io/nvidia-docker/$distribution/nvidia-docker.list | sudo tee /etc/apt/sources.list.d/nvidia-docker.list
sudo apt-get update && sudo apt-get install -y nvidia-container-toolkit # nvidia-container-toolkit installation
sudo /etc/init.d/docker restart
More...
-
ECG5000 Data download from
timeseriesclassification
Execute./data.bat
-
Install library using
pip install -r requirements.txt
-
Execute
julia requirements.jl
(install lib) -
Execute
python julia_setting.py
-
Execute python file
python train.py
-
You can modify VMD setting or AI model via
./utils/util.py
and ./utils/preprocessing.jl
and ./models/model.py
More...
-
ECG5000 Data download from
timeseriesclassification
Executesh data.sh
-
Install library using
pip install -r requirements.txt
-
Execute
julia requirements.jl
(install lib) -
Execute
python julia_setting.py
-
Execute python file
python train.py
-
You can modify VMD setting or AI model via
./utils/util.py
and ./utils/preprocessing.jl
and ./models/model.py
More...
-
ECG5000 Data download from
timeseriesclassification
Executesh data.sh
-
if Docker turn off, Execute
sudo service docker start
-
Execute
docker build -t nn-vmd .
-
Execute GPU version
docker run -it --gpus all --name nn-vmd nn-vmd:latest bash train.sh
(default : MTL)Execute CPU version
docker run -it --name nn-vmd nn-vmd:latest bash train.sh
-
Option Execute
docker start nn-vmd (required)
docker exec -it nn-vmd bash train.sh cnn
docker exec -it nn-vmd bash train.sh vae
- VAE (Variational Auto Encoder)
- Graph neural nets + Shallow neural nets
- Multi-task learning (e.g. decomposition and classification task)
@inproceedings{han2022ai,
title={AI model based variational mode decomposition using signal data},
author={Han, Seungwoo},
journal={proceedings of symposium of the korean institute of communications and information sciences},
pages={1362--1363},
year={2022}
}