Link: https://github.com/TopoXLab/TopoGAN-ECCV2020

Sorry if this is the wrong place to ask, but I've been looking for help on how to work this out for a long time as I don't have much experience in these matters. As said in the README, I've imported the required libraries and set the Hyperparameters (I didn't touch any topology setting, I just set file directories). Then I went to the main notebook Example.ipynb file here, but it's not clear which cells should be run and how, if I want to generate images based on a dataset that I already have. The only information provided was that "The datasets are preprocessed and subsampled to have a smaller patch size and compatible form. The persistence diagrams of the training images should be pre-computed with the function "FileIO.compute_pd_save" An example is given in the Main.ipynb." So, I computed presistence diagrams with this cell in Example.ipynb, but I don't know how to use it to train the network and generate images.

Compute and save persistence diagrams for training images
%run FileIO.ipynb
%run Archpool.ipynb

root = 'D:/Data/facades/facade128'
adv_params = return_advanced_params()
FileIO.compute_pd_save(root, root+'/pds', "jpg", adv_params, 1, 127.5)


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.