In this tutorial you will find all the steps and instructions you need in order to reproduce the experiments performed in "Maximum Entropy on Erroneous Predictions (MEEP)"
The code has been written in Python (3.6) and requires TensorFlow (2.3) You should also have installed the requirements:
pip install -r requirements.txt
First, make sure that the folder data contains the download the dataset.
Make sure you choose the desired loss dunction and parameters in the file, then The model can be trained using below command:
python training.py