Stuck at: Reading video frames from start...
anderoavv opened this issue · comments
Hey!
Any idea why the demo video&audio files just get stuck(just installed and wanted to test demo out)? It's been like this for 10minutes.
Edit:
Ok finally it moved. I have to see what I can do on Azure:
Using cpu for inference.
(80, 561)
Length of mel chunks: 206
0%| | 0/2 [00:00<?, ?it/s]Reading video frames from start...
Loading segmentation network...
Downloading: "https://download.pytorch.org/models/resnet18-5c106cde.pth" to /home/azureuser/.cache/torch/hub/checkpoints/resnet18-5c106cde.pth
100%|█████████████████████████████████████| 44.7M/44.7M [00:00<00:00, 103MB/s]
0%| | 0/2 [12:27<?, ?it/s]
Traceback (most recent call last):
File "inference.py", line 359, in
main()
File "inference.py", line 296, in main
seg_net = init_parser(args.segmentation_path)
File "/home/azureuser/Wav2Lip-HD/face_parsing/swap.py", line 12, in init_parser
net.cuda()
File "/home/azureuser/.local/lib/python3.8/site-packages/torch/nn/modules/module.py", line 905, in cuda
return self._apply(lambda t: t.cuda(device))
File "/home/azureuser/.local/lib/python3.8/site-packages/torch/nn/modules/module.py", line 797, in _apply
module._apply(fn)
File "/home/azureuser/.local/lib/python3.8/site-packages/torch/nn/modules/module.py", line 797, in _apply
module._apply(fn)
File "/home/azureuser/.local/lib/python3.8/site-packages/torch/nn/modules/module.py", line 797, in _apply
module._apply(fn)
File "/home/azureuser/.local/lib/python3.8/site-packages/torch/nn/modules/module.py", line 820, in _apply
param_applied = fn(param)
File "/home/azureuser/.local/lib/python3.8/site-packages/torch/nn/modules/module.py", line 905, in
return self._apply(lambda t: t.cuda(device))
File "/home/azureuser/.local/lib/python3.8/site-packages/torch/cuda/init.py", line 247, in _lazy_init
torch._C._cuda_init()
RuntimeError: No CUDA GPUs are available
run_final.sh: line 11: python: command not found
run_final.sh: line 13: python: command not found
It is GPU error, please use GPU.
It is GPU error, please use GPU.
Hello @saifhassan how to make it use GPU?
It's mine worked yesterdya but not today:
Error CUDA out of memory. Tried to allocate 15. GiB. GPU 0 has a total capacty of 23.99 GiB of which 0 bytes is free. Of the allocated memory 21.00 GiB is allocated by PyTorch,
I restarted computer to make sure nothing is interfering...