Assaf Shocher

Hi, I am not familiar with such problem, let's review some possible directions. Since the folder was formed and code was copied into it, I believe this is not an...

Stay tuned, an even better one will most likely be released in a month or so.

Check this out: http://www.wisdom.weizmann.ac.il/~vision/kernelgan/

Sure, you can just change this option in the config file

Hi, It looks like you mistakenly deleted a character. The error you got is saying: > File "C:\Users\15479\Desktop\ZSSR\utils.py", line 192, in prepare_result_dir > if conf.create_result_dir: > AttributeError: 'Config' object has...

You will also have a bit of trouble with py version (see other issues I resolved. Mind mostly for division / ). But note how the quoted code is not...

If I remember correctly: 1. We used a grayscale version of the image for all three channels. 2. Applied ZSSR and EDSR to the same image. 3. Then created a...

Thanks for replying! I'm using BatchedEDplus because of the size. Should I be using BatchedED? Re ill-conditioned: when testing the same matrix out of the batch, or even when just...

[mat.pt.zip](https://github.com/KingJamesSong/BatchED/files/11127574/mat.pt.zip) Here is an example tensor that fails. To reproduce, first extract it and then: ``` mat = torch.load('mat.pt') eig_vecs, eig_diag = batched_ed_plus(mat) eig_vecs_.isnan().nonzero() # (result shows all eigen vecs...

Thanks for your response! Decreasing epsilon in those lines only seemed to make it worse (when training the model encountered NaN much earlier). I tried increasing it to e-3 which...