Closed JR-Wang closed 4 years ago
Did you use the pretrained model (generator_checkpoint_singleGPU.ckpt)? The other model is a distributed trained version.
Many thanks for your timely reply! Below is my last operation. python eval.py --data-path './dataset' --checkpoint-path 'CHECKPOINT_PATH/generator_checkpoint.ckpt' I changed the model to generator_checkpoint_singleGPU.ckpt and got correct result. So I wonder if you may revise your README?
Sure, There was a mistake. Thank you for your feedback :)
I tried your eval.py,but predicted_image seems to be a picture of noise. I have confirmed input_image got from the code below, input_image = input_image.to(device) if step==1: target_image = x2_target_image.to(device) elif step==2: target_image = x4_target_image.to(device) else: target_image = target_image.to(device)
and it is a 16*16 image. May I ask what's wrong with my predicted_image? Many thanks for your answer.