Input images larger than 512x512?

[sjscotti]

Hi!
I am very impressed by the capabilities of HiFaceGAN!
However, I tried to process an image larger than 512x512 in size - changing the values of crop_size and prd_resize in config_hifacegan.py to the size of my image - and it scaled the results back to 512x512. Is there something else I need to do to process larger images in the code?
Thanks!

[nikhilweee]

@sjscotti Apart from changing dataset_mode to test_nogt (which I think you already did), maybe you can change num_upsampling_layers to more or most according to your need. But AFAIK none of the pretrained models support more than 1024. I might be wrong here. Maybe one of the owners can provide a better answer.

[nikhilweee]

Update: I found it. Change 512 to whatever resolution that you desire.

Face-Renovation/data/testnogt_dataset.py

Line 51 in d799660

image = cv2.resize(zero, (512,512), cv2.INTER_CUBIC)

Also, do not forget to change crop_size accordingly in the options.

[sjscotti]

Thanks @nikhilweee !