Setup

DeePCK is available for Python 3.8+ on Linux, macOS and Windows.

Install with conda

  1. Install numpy and visualization packages for basic usage.

conda install numpy matplotlib seaborn

  1. DeePCK depends on cantera, so use cantera/label/dev channel to install cantera .

conda install --channel cantera/label/dev cantera

  1. The implementation of Model Module is based on the deep learning framework pytorch, install pytorch CPU version via conda.

conda install pytorch

  1. Note: if you prefer training the DNN model on GPU, you might need to install pytorch GPU version. The GPU version requires compatible NVIDIA drivers to be installed already. Therefore, check the CUDA driver version on your platform and see the installation guide on Pytorch offical website. For CUDA version 10.1, run the command for instance:

conda install pytorch=1.7 torchvision cudatoolkit=10.1 -c pytorch

  1. easydict allows to access dict values as attributes and then install it via conda :

conda install -c conda-forge easydict

or via pip :

pip install easydict

  1. (optional) If you are working on the HPC Clusters scheduled with slurm system, it is highly recommended to install mpi4py for massive parallelization via conda (especielly for Data Module). Check mpi4py documentation for more instruction.

conda install -c conda-forge mpi4py openmpi

Install with docker

To be continued.