Going through the demo but no files

[miladavaz]

Succesfully going through the demo with zero errors, but getting no output in any of the created folders.

[zhangmozhe]

Do you use the colab demo as is? We do not come across such issue. Can you please post more information or share the demo link to us?

[miladavaz]

Hey, Im not using the colab, but the local install.

Here is the excerpt when I run the code. all things seem to be going well (i know it also tries to treat the .dsstore file but that shouldnt be any issue here.

Macbook:Bringing-Old-Photos-Back-to-Life username$ pipenv run python run.py --input_folder alfa --output_folder alfa/done --GPU -1
Running Stage 1: Overall restoration
Traceback (most recent call last):
  File "/Users/username/Desktop/coding/photosave/Bringing-Old-Photos-Back-to-Life/Global/test.py", line 131, in <module>
    input = Image.open(input_file).convert("RGB")
  File "/Users/username/.local/share/virtualenvs/Bringing-Old-Photos-Back-to-Life-5q-Oxyjf/lib/python3.9/site-packages/PIL/Image.py", line 2958, in open
    raise UnidentifiedImageError(
PIL.UnidentifiedImageError: cannot identify image file '/Users/username/Desktop/coding/photosave/Bringing-Old-Photos-Back-to-Life/alfa/.DS_Store'
Finish Stage 1 ...


Running Stage 2: Face Detection
Finish Stage 2 ...


Running Stage 3: Face Enhancement
dataset [FaceTestDataset] of size 0 was created
The size of the latent vector size is [8,8]
Network [SPADEGenerator] was created. Total number of parameters: 92.1 million. To see the architecture, do print(network).
hi :)
Finish Stage 3 ...


Running Stage 4: Blending
Finish Stage 4 ...


All the processing is done. Please check the results.
Macbook:Bringing-Old-Photos-Back-to-Life username$ 

[AdrianDSW]

I met the same problem, too. my tree👇 . ├── in │   └── src.jpg └── out ├── final_output ├── stage_1_restore_output │   ├── input_image │   ├── origin │   └── restored_image ├── stage_2_detection_output └── stage_3_face_output └── each_img

[rn54n]

Hi,

so you are using Mac OS X - I solved it by editing Global/test.py adding an extension variable and checked if filename with last 3 digits is in list ext => " if input_name[-3:] in ext:"

  mask_transform = transforms.ToTensor()
  ext=['jpg','png','gif']
  for i in range(dataset_size):
    input_name = input_loader[i]
        if input_name[-3:] in ext:
            input_file = os.path.join(opt.test_input, input_name)
            if not os.path.isfile(input_file):
                print("Skipping non-file %s" % input_name)
                continue
            input = Image.open(input_file).convert("RGB")
            print("Now you are processing %s" % (input_name))