Joonhyung Lee/이준형

@One-sixth Hello. Thank you for the information on performance. I am glad to know this. As for the small increase in time, I think that expanding the kernel in ssim()...

@One-sixth Does the new implementation use dynamic value scaling by any chance? I implemented the value range to be the range of values for the target if the value range...

@One-sixth Thanks for the update! I have one more question. Do both versions use the 'compensation' variable? Transferring data from CPU to GPU is actually a very expensive operation and...

@One-sixth I was referring to the variable `compensation = 1.0` in ssim.py. However, I checked and both versions have the variable.

@lintongtong123 @planewave @harritaylor @obilaniu There is a very (extremely) basic implementation in Pytorch [here](https://github.com/litcoderr/ComplexCNN). @chris1992212 Also, a slightly less basic implementation in Tensorflow was made [here](https://github.com/CedricChing/DeepMRI/blob/master/model.py). I recall that there...

Hello! Thank you for the great project. I would like to mention a little bugbear with the Black code style that I have. Black currently formats functions such that arguments...

Also, the PyInk project https://github.com/google/pyink has some good ideas for which configurations should be allowed.

@helderco I agree that using PyInk as a benchmark would not be a good idea and that having too many options would be a bad idea. Still, I believe that...

From what I could gather from the conversation in https://github.com/psf/black/issues/1178, Black continues to use its current indentation for arguments as changing it would be too disruptive, even though it diverges...

Thank you for the help! Unfortunately, I have found that this still requires manual editing of the model because parts such as the rotary embedding expect BF16.