face_detector_module = import("face_detection.detection." + face_detector,
globals(), locals(), [face_detector], 0)
self.face_detector = face_detector_module.FaceDetector(device=device, verbose=verbose) What is the problem? Thank you
ERROR: Ignored the following versions that require a different python version: 1.25.0rc1 Requires-Python >=3.9
ERROR: Could not find a version that satisfies the requirement opencv-python==18.104.22.168 (from versions: 22.214.171.124, 126.96.36.199, 188.8.131.52, 184.108.40.206, 220.127.116.11, 18.104.22.168, 22.214.171.124, 126.96.36.199,...
Thank you so much for your efforts in creating the demo and video. Very helpful material and clear instructions to follow.
I created a 4s mp4 video and a 11s wav audio file and tried to sync them using the interactive demo. Unfortunately I could not get anything.
Then I decided to download the dicta...
return self._apply(lambda t: t.cuda(device))
File "\wav2liphp\lib\site-packages\torch\cuda_init_.py", line 239, in _lazy_init
raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA enabled
My PC is Intel R lris Xe Graphics ,help me
I tried using the pre-trained syncnet model on a subset of the AVSpeech dataset. The videos that I chose from AVSpeech were 25FPS videos. In color_syncnet_train.py, I tried turning off backpropagation in order to see the loss the pre-trained model had on those videos, either with an in-sync pair or...