DeepEnhancer

[Selur]

Installing looseversion

python -m pip install looseversion

and changing "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\basicsr\archs\arch_util.py", line 6, from

from distutils.version import LooseVersion

seems to fix the above problem.
But now calling:

SET CUDA_VISIBLE_DEVICES=0 python Lib\site-packages\DeepEnhancer\test_demo.py

doesn't output anything.
Removing 'SET CUDA_VISIBLE_DEVICES=0' does seem to start, but stops after:

Traceback (most recent call last):
  File "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\DeepEnhancer\test_demo.py", line 14, in <module>
    from basicsr.data.film_dataset import resize_240_short_side
  File "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\basicsr\__init__.py", line 4, in <module>
    from .data import *
  File "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\basicsr\data\__init__.py", line 22, in <module>
    _dataset_modules = [importlib.import_module(f'basicsr.data.{file_name}') for file_name in dataset_filenames]
                        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "importlib\__init__.py", line 90, in import_module
  File "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\basicsr\data\realesrgan_dataset.py", line 11, in <module>
    from basicsr.data.degradations import circular_lowpass_kernel, random_mixed_kernels
  File "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\basicsr\data\degradations.py", line 8, in <module>
    from torchvision.transforms.functional_tensor import rgb_to_grayscale
ModuleNotFoundError: No module named 'torchvision.transforms.functional_tensor'

The torchvision.transforms.functional_tensor module was removed in 0.17.
Current dev torch-add-on uses:

torchvision                 0.22.0.dev20250325+cu128

=> Not looking into this further.

Cu Selur