search

Junshk / CinCGAN-pytorch

Unofficial Implementation of "Unsupervised Image Super-Resolution using Cycle-in-Cycle Generative Adversarial Networks" in CVPR 2018.
142 stars 27 forks source link

Pretrained EDSR model #6

Closed fredlll closed 5 years ago

fredlll commented 5 years ago

Hi is the download link downloading the correct model? The names of the downloaded model is EDSR_x4.py insteand of EDSR_baseline_x4.pt as suggested in the code.

After I renamed the file. It seems the model dimension does not match.

Traceback (most recent call last): File "/home/shitaili/workspace/jupyter_notebooks/sr/CinCGAN-pytorch/code/model/edsr.py", line 65, in load_state_dict ownstate[name].copy(param) RuntimeError: The expanded size of the tensor (64) must match the existing size (256) at non-singleton dimension 0. Target sizes: [64, 3, 3, 3]. Tensor sizes: [256, 3, 3, 3]

fredlll commented 5 years ago

Okay I realized I should use the setting of this line from demo.sh :

EDSR in the paper (x4) - from EDSR (x2)

AbdelsalamHaa commented 4 years ago

Hi @fredlll I'm facing the same issue, but I can't find a file named demo.sh