ICT
ICT copied to clipboard
Pretrained weight of upsampler of Places does not work well.
Hi, @raywzy
I tried to use both FFHQ and Places2 pretrained weights of upsampler. However, the Upsampler's pretrained weight of Places does not have enough quality. We know that the weight of the generator is trained during 322000 iterations. Do you think that the attached results are correct?
From left to right, 1st stage output | blended result with masked input image | raw output of upsampler | GT image | masked input image | raw output of upsampler within given mask
Hello, May I ask if you encountered this error again when running this code?
when I am running
the error message shows this. How can I modify the error