ujjawal-k-panchal / coshnet Goto Github PK

I saw a link to your paper on Twitter and have been digging into the code! I noticed there are placeholders for RGB and Lab support in various places already, but it doesn't seem complete.

What would be necessary to support 3 input channels and beyond? Also, what if the images are more than 32x32 — do you recommend using a patch-based representation like ViT?

(I guess this is a likely future path for the research, so if you're working on it that's very interesting!)

Even when we pass --dataset mnist to test_fashion.py, the initial download downloads the Fashion MNIST dataset and downloads it within MNIST directory. This is because, load_fashion() function is not passing kFashion parameter to getdb() function. This is causing kFashion to default to true and for the URL fetched for downloading the dataset to be Fashion MNIST url even if the user wished for MNIST url.

How accurate should the reconstructions be? I'm trying out shearrec2D after the sheardec2D and the results aren't as good as I would have expected — even bumping up the number of different shearlets.

Are other filters needed in combination with shearlets to get good reconstructions?

Thanks!

I'm visualizing the shearlets generated and either I'm doing something wrong or I'm not sure that shearing is being applied as intended.

From debugging, it seems the shearing itself does work, but it's shearing the shearlets in the wrong direction: horizontal shearlets sheared horizontally, and vertical shearlets sheared vertically makes it a no-op basically.

Have you checked this works in the current repository?