Pytorch implementation of i-RevNets
i-RevNet: Deep Invertible Networks
Pytorch implementation of i-RevNets.
i-RevNets define a family of fully invertible deep networks, built from a succession of homeomorphic layers.
Reference: Jörn-Henrik Jacobsen, Arnold Smeulders, Edouard Oyallon. i-RevNet: Deep Invertible Networks. International Conference on Learning Representations (ICLR), 2018. (https://iclr.cc/)
The i-RevNet and its dual. The inverse can be obtained from the forward model with minimal adaption and is an i-RevNet as well. Read the paper for theoretical background and detailed analysis of the trained models.
Pytorch i-RevNet Usage
Requirements: Python 3, Numpy, Pytorch, Torchvision
Download the ImageNet dataset and move validation images to labeled subfolders.
To do this, you can use the following script: https://raw.githubusercontent.com/soumith/imagenetloader.torch/master/valprep.sh
We provide an Imagenet pre-trained model: Download
Save it to this folder.
Train small i-RevNet on