Installation

This page provides information on how to install Jolideco. In general it is recommended to use a virtual environment to install Jolideco. This can be done using conda or virtualenv.

Then to install Jolideco, you can use pip:

python -m pip install jolideco

When you encounter problems during the installation especially with Pytorch, it is recommended to first install Pytorch, using the more detailed instructions on the Pytorch webpage.

Jolideco relies on pre-train Gaussian Mixture Models (GMM) to estimate the prior distribution of the parameters of the model. These GMM are stored in a separate repository.

To install the patch prior library, just clone the following repository:

git clone https://github.com/jolideco/jolideco-gmm-prior-library.git
export JOLIDECO_GMM_PRIOR_LIBRARY=/path/to/jolideco-gmm-prior-library

And define the environment variable JOLIDECO_GMM_PRIOR_LIBRARY to point to the folder where you cloned the repository.

You can verify that the installation was successful by running the following command:

jolideco test

If all tests pass, the installation was successful and you are ready to go!

What’s next?

📚 If you would like to first learn Jolideco on example datasets checkout the Tutorials.

🚀 If you would like to directly start with your own data, rather checkout the Getting Started page.