raymondyeh07 / tv_layers_for_cv Goto Github PK

Thanks for the amazing work!

I was wondering if you guys have also tried to write an implementation where D can be fed into the TV layer as a parameter and get gradients for the corresponding D matrix? (Specifically D could be parameterized using a 1xN vector or 2xNxC (N=kernel length (say 2 or 3), C=number of channels) which is what would be fed in and used for gradient computation.

And if I had to try to implement that on top of your current implementation, could you point me towards how I could go about it? Thanks!

There are the following problems when installing according to the method you provided.

The above situation still occurs when the calculation force is set to 8.0 or 7.5.
The following error occurred after changing ['ninja', '-v'] to ['Ninja','-version'].

Could you please share the complete file directory after compilation?
GPU：RTX3090
Linux：Ubuntu18.04

Thank you for your awesome works!
I follow your tutorial, but when I run python setup.py install, this problem as title has shown. And my gcc version is 9.4.0.
Can you check out some dependency of your code?

hi, can you explain the difference between your method and simply adding a TV loss? Thank you.