Implementation of Invertible Neural Networks (INNs) based on Ardizzone et al. (2019) using TensorFlow2 + Keras

This repository includes the code example of the invertible neural networks (Ardizzone et al., 2019) implemented using TensorFlow2 with Keras. Two complementary coupling layers were implemented and toy examples were provided similar to the paper. The current code is largely based on the original PyTorch implementation by the authors, but simplified for the easier understanding than the original code and for the personal use.

2020-11-26 first created

Open in Colab:

Original works:

• Paper: http://arxiv.org/abs/1808.04730
• Code: https://github.com/VLL-HD/analyzing_inverse_problems

TODO:

• Add the inverse kinematics example

Reference:

• Ardizzone, L., Kruse, J., Wirkert, S., Rahner, D., Pellegrini, E. W., Klessen, R. S., Maier-Hein, L., Rother, C., & Köthe, U. (2019). Analyzing inverse problems with invertible neural networks. 7th International Conference on Learning Representations, ICLR 2019, 1–20.