felime / audiostylenet Goto Github PK

Interested in running the colab demo with a custom image, would I need to use resnetEncoder to convert my image into latent space. If so, where can I find the pretrained weights for the resnetEncoder?

I can not download the dataset, can anyone share it

i running the '$ python run_audiostylenet.py' cmd and got demo01.avi, but the file only 1 second
what can i do for this?

First, I compiled the 'fused' op and install the missing face_alignment:

  cd op && python setup.py install
  pip install face_alignment

Then, this error occurred:

FileNotFoundError: [Errno 2] No such file or directory: 'model/audio2expression_convNet_justus.pt'

This model file is missing in google drive.

I cannot run the code because of this problem. Hope you can explain in detail, thank you.