I’m completely new to all this and I keep getting the same error feedback when I’m running the final download step.

zip_filename = 'Real-ESRGAN_result.zip'
if os.path.exists(zip_filename):
  os.remove(zip_filename)
os.system(f"zip -r -j {zip_filename} results/*")
files.download(zip_filename)

Feedback:

FileNotFoundError                         Traceback (most recent call last)
<ipython-input-8-a16867ab1a8a> in <cell line: 6>()
      4   os.remove(zip_filename)
      5 os.system(f"zip -r -j {zip_filename} results/*")
----> 6 files.download(zip_filename)

/usr/local/lib/python3.10/dist-packages/google/colab/files.py in download(filename)
    231   if not _os.path.exists(filename):
    232     msg = 'Cannot find file: {}'.format(filename)
--> 233     raise FileNotFoundError(msg)  # pylint: disable=undefined-variable
    234 
    235   comm_manager = _IPython.get_ipython().kernel.comm_manager

FileNotFoundError: Cannot find file: Real-ESRGAN_result.zip

I’ve gotten the following error feedback when running the inference step:

ModuleNotFoundError: No module named ‘torchvision.transforms.functional_tensor’

I wasn’t sure if it was the reason for the issue later, but this above feedback persists when I force a reinstallation of PyTorch and TorchVision. I have already verified their compatibility.

Again, the error in the download step is 100% reproduceable while running the original code on T4 GPU.