Multi-class classification with focal loss for imbalanced datasets | DLology Blog

How to Run

Clone or download this repo

git clone https://github.com/Tony607/Focal_Loss_Keras

Install required libraries

pip install -r requirements.txt

Download the fraud data set from Kaggle and extract the csv file to input folder in the project directory. https://www.kaggle.com/ntnu-testimon/paysim1

In the project start a command line, run

jupyter notebook

For baseline model, in the opened browser window open

keras_base_line.ipynb.ipynb

For focal loss model, open

keras_focal_loss.ipynb

Happy coding! Leave a comment if you have any question.