GTDA-based ReebNet for full ImageNet data with ResNet, VOLO, and AlexNet

This folder is used to produce the experiments of ImageNet reported in paper Topological structure of complex predictions. A preprint version of the paper is available on arXiv: https://arxiv.org/abs/2207.14358

Unzip the three .tar.gz files. At the end, you should have a directory that looks like:

• exp_comparison_plotting_resnet_alexnet.py
• exp_comparison_plotting_volo_resnet.py
• GTDA
• GTDA.tar.gz
• GTDA.yml
• ImageNet
• ImageNet-details.txt
• meta.mat
• README.txt
• resnet_alexnet
• resnet_alexnet.tar.gz
• volo_resnet
• volo_resnet.tar.gz

The ImageNet files are too large to include and are available from many other sources. You can verify you have the right setup by checking the ImageNet-details.txt file, which has the sha sum for each file we used along with the directory structure. 

There are additional instructions inside the REAMDE.txt file on how to setup the python environment to reproduce the figures.