We list the table of contents here.
.
    - ./Data 
        - Phase_diagram: numpy array for data used for phase diagrams.
        - Training: numpy array for training accuracies.

    - ./Notebooks
        - Demo.ipynb: a quick notebook to reproduce most of our plots, it takes around 20 min to run on a cpu.
        - phase_diagrams_and_training_results.ipynb: load data from './Data/Training' and './Data/Phase_diagram' to make phase diagrams and check accuracies.

    - ./utils
        - partialjaclib.py: our customized library, needed to run the 'Demo.ipynb' notebook. All models and functions we wrote are in this file.

    - Training_MLP_Fig2_Column1to3.py: learning rate search and training codes for first three rows of Fig 2. Need to change activation by hand.

    - Training_MLP_Fig2_Column4.py: learning rate search and training codes for last row of Fig 2.

    - Training_Mixer_Fig3: Mixer training file for Fig 3. Hyperparameters need to be adjusted by hand.
