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

<p>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</p><p>Unzip the three .tar.gz files. At the end, you should have a directory that looks like:</p><ul><li>exp_comparison_plotting_resnet_alexnet.py</li><li>exp_comparison_plotting_volo_resnet.py</li><li><strong>GTDA</strong></li><li>GTDA.tar.gz</li><li>GTDA.yml</li><li><i>ImageNet</i></li><li>ImageNet-details.txt</li><li>meta.mat</li><li>README.txt</li><li><strong>resnet_alexnet</strong></li><li>resnet_alexnet.tar.gz</li><li><strong>volo_resnet</strong></li><li>volo_resnet.tar.gz</li></ul><p>The <i>ImageNet</i> 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.&nbsp;</p><p>There are additional instructions inside the REAMDE.txt file on how to setup the python environment to reproduce the figures.&nbsp;</p><p>&nbsp;</p><p>&nbsp;</p>