nmndeep

A simple fix that worked for me in the current version of code. Replace this [line](https://github.com/IceClear/CLIP-IQA/blob/061fd3c7b1b40839959777897c764792760d693c/mmedit/models/restorers/basic_restorer.py#L34) with `` allowed_metrics = {'PSNR': psnr, 'SSIM': ssim, 'L1DIS': l1dis} `` and import ``l1dis``...

Hi, For training with ViT-S, we used ``deit_s`` from [here](https://github.com/nmndeep/revisiting-at/blob/b963afb6082d7bb51d129598fe7eb1a19750e78a/utils_architecture.py#L277C20-L277C21) And the specific key was`deit_small_patch16_224` - this should also be listed in the appendix. I think the confusion stems from...

Hi, I cannot say surely what the reason for certain behaviour is and I do not know the full setting you worked with. Note, we used 2-step APGD not PGD...

Hi, We do post-hoc best checkpoint selection with a few step APGD(try 1 or 5-step) for Linf-norm on a separate validation set as opposed to the RobsutBench test set. I...

Hi, Thanks for using our models, seems to be a version issue with torch. Some people have reported this for other intances: [here](https://github.com/huggingface/pytorch-image-models/discussions/749) I was able to load the same...

[main_py.yml.zip](https://github.com/nmndeep/revisiting-at/files/14423866/main_py.yml.zip) Here is my environment - works for me here, hope this helps.

fee free to reopen for any other query