Variational Deep Learning models for non Euclidean structure

Click on the following link to access further information on mathematical presentation of variational autoencoder https://github.com/kbronik2017/Non_Euclidean_UCL/blob/main/references/Auto-Encoding.pdf

Click on the following link to access further information on mathematics of analytical methods https://github.com/kbronik2017/Non_Euclidean_UCL/blob/main/references/Squartini_2011_New_J._Phys._13_083001.pdf

Undirected Configuration Model (UCM)

Weighted Configuration Model (WCM)

Reciprocal Configuration Model (RCM)

Reonstruction Network (RCON)

Parallel running

Running the GUI Program!

First, user needs to install Anaconda https://www.anaconda.com/

Then

  - conda env create -f train_test_environment.yml
  or
  - conda create --name idp --file clone-file.txt

and

  - conda activate idp

finally

  - python  VAE_GUI.py

After lunching the graphical user interface, user will need to provide necessary information to start training/testing as follows:

Testing the Program (User Quick Start Guide)

Examples of Training, Cross-validation and Testing subjects can be found in: https://github.com/kbronik2017/Non_Euclidean_UCL/tree/main/training_testing_examples (which will allow users to quickly and easily train and test the program). The results of testing(inference) can be found in the folders:

  - prediction_image_outputs
  and
  - matrix_output