HarukiYqM/Non-Local-Sparse-Attention

The number of NLSN operations?

Closed this issue · 2 comments

C-water commented

Hi,
I set res_block=32, so the model should contain 5 NLSA modules. When I send an image to the model, it should go through 5 NLSA runs, but when I counted the NLSA runs, I found that the NLSA runs 20 times. Why?
For each image, run the model 4 times to calculate the average PSNR?

Thank you.

HarukiYqM commented

Because the —chop flag splits the images into four parts to handle large size input. This is a widely used strategy in image super-resolution algorithms.

  • 👍1
C-water commented

Thank you for your help