when i do try restored image then in inference became like this. how do i fix this? thank you

[joey4411]

when i do try restored image then in inference became like this. how do i fix this? thank you

[cperry-goog]

We'll need a minimal reproducible notebook to investigate, or contact the original notebook author.

[cperry-goog]

Okay a bit more info after one of our eng looked (thanks!)

It looks like you're following this notebook, but the torchvision api has been deprecated. The correct issue to upvote is here: TencentARC/GFPGAN#539

In the meantime you can clone the repo and change the code as described here: AUTOMATIC1111/stable-diffusion-webui#13985 (comment)

As this does not appear to be a Colab issue, I'm closing this.

[shishirahm3d]

@joey4411 run this code on colab before running 3. Inference. it will replace the degradation.py line 8
from torchvision.transforms.functional_tensor import rgb_to_grayscale
to:
from torchvision.transforms.functional import rgb_to_grayscale

then you're good to go...

# Define the file path
file_path = '/usr/local/lib/python3.10/dist-packages/basicsr/data/degradations.py'

# Define the new import statement
new_import_statement = "from torchvision.transforms.functional import rgb_to_grayscale\n"

# Read the content of the file
with open(file_path, 'r') as file:
    lines = file.readlines()

# Modify the desired line (line 8 in this case)
if len(lines) >= 8:
    lines[7] = new_import_statement  # Index 7 corresponds to line 8 (0-based indexing)

# Write the modified content back to the file
with open(file_path, 'w') as file:
    file.writelines(lines)

print("Replacement completed successfully!")

[joey4411]

thanks a lot it fixed now 👍