how to test a image which resolution is not (256,256)?

[shiguangliuguo]

hi there, thanks for your job for offerring a script "test_in_any_resolution.py"
but, in this script, a image with random size has been processed in expand2square function,
but such size cant feed into the Uformer model.

so i wonder if this network cant process the size isn't (256,256)?
if i want to denoise the image with random size, i have to resize the size of image to (256,256)?
thanks!

[KB-co]

It is an important question...

[vinthony]

Hi, as illustrated in test_in_any_resolution.py, the input images can be in any size, and then, we pad them to the X times of the 256 to fit our network. NOT 256x256 as input. After getting the results, we can use the mask to mask out the paddings.

[ElMalickG]

Hi, as illustrated in test_in_any_resolution.py, the input images can be in any size, and then, we pad them to the X times of the 256 to fit our network. NOT 256x256 as input. After getting the results, we can use the mask to mask out the paddings.

Hi, Congrats for the nice job you have done !
I would like to know where to find the "test_in_any_resolution.py" script. Thanks