Testing without GT about hcflow HOT 4 CLOSED

Thank you for reporting the bug. We have fixed it. Please use the updated code ( we updated GT_dataset.py, LQ_dataset.py, HCFlow_SR_model and test_HCFlow.py), and then use dataloader mode LQ to test without GT.

from hcflow.

Thank you, the problem has been solved for both the face image SR and general image SR. Image rescaling gives AttributeError: 'HCFLowRescalingModel' object has no attribute 'real_H'

in "HCFlow_Rescaling_model.py", in line 312

from hcflow.

This is because there is no meaning to do so for the rescaling task.

Image rescaling aims to downscale the HR image to a visually meaningful LR image, and then recover the HR image plausibly. Different from image SR that works on a given LR image space, image rescaling tries to maintain as much information from the HR image as possible for a better subsequent reconstruction, for the purpose of reducing the storage and bandwidth cost. In other words, it can define its own LR image space which is expected to be more informative than that by simple downscaling such as bicubic downscaling.

Therefore, inputting a LR image for testing is meaningless. You can try to use GT_dataset.py to input a HR image for testing.

from hcflow.

@JingyunLiang Thank you for the clarification

from hcflow.