Inference results conflict?

[innat]

Interesting work. Thanks for sharing.

However, I have tried to inference on some samples with the provided pretrained weights. But for some reason, I couldn't get the expected results. I tried with both executable files and also source files. For example, while using source files, I have checked both weights (DF2K.pth and DPED.pth). Please see below:

Input

Using DF2K

Using DPED

Now, as it's demonstrated the visual results here, I expected the same or reasonable results. Any catch?

Apart from this, here is another issue, in the testing time, isn't it possible to place multiple low-resolution images at a time? For example, as demonstrated here, if I place (let's say) 5 images in 'dataroot_LR' -- test images dir; it throws CUDA out of memory: RunTimeError.

[usstdqq]

you got an oom error as the error message suggested... what's your image resolution and GPU memory... you can try to input 5 100x100 resolution images and it should be fine.

[innat]

I got errors for trying to inference more than one image. Let's forget that for now. I'm getting the above result from one image, any catch?.

[usstdqq]

your LR input image has some blocking artifacts already and is prob different from the distribution of the LR training data. can you try to downsample the image by a factor of 2 or 4 and try again? those blocking artifacts might be surpressed by downsampling.