search

joonson / syncnet_python

Out of time: automated lip sync in the wild
MIT License
652 stars 146 forks source link

Demo Not Working (RuntimeError: mat1 dim 1 must match mat2 dim 0) #30

Closed avisekiit closed 3 years ago

avisekiit commented 4 years ago

Dear Authors, Firstly, thanks for releasing the codes and the models.

I could run your demo code with the data/example.avi as suggested in the readme. However, when I try to run that same demo with one of my .avi files, I get the below runtime error. Here is my video file Any guidance to mitigate this will be really appreciated.

Traceback (most recent call last): File "demo_syncnet.py", line 30, in <module> s.evaluate(opt, videofile=opt.videofile) File "/data/syncnet_python/SyncNetInstance.py", line 112, in evaluate im_out = self.__S__.forward_lip(im_in.cuda()); File "/data/syncnet_python/SyncNetModel.py", line 108, in forward_lip out = self.netfclip(mid); File "/usr/local/google/home/avisek/anaconda2/envs/syncnet/lib/python3.6/site-packages/torch/nn/modules/module.py", line 722, in _call_impl result = self.forward(*input, **kwargs) File "/usr/local/google/home/avisek/anaconda2/envs/syncnet/lib/python3.6/site-packages/torch/nn/modules/container.py", line 117, in forward input = module(input) File "/usr/local/google/home/avisek/anaconda2/envs/syncnet/lib/python3.6/site-packages/torch/nn/modules/module.py", line 722, in _call_impl result = self.forward(*input, **kwargs) File "/usr/local/google/home/avisek/anaconda2/envs/syncnet/lib/python3.6/site-packages/torch/nn/modules/linear.py", line 91, in forward return F.linear(input, self.weight, self.bias) File "/usr/local/google/home/avisek/anaconda2/envs/syncnet/lib/python3.6/site-packages/torch/nn/functional.py", line 1674, in linear ret = torch.addmm(bias, input, weight.t()) RuntimeError: mat1 dim 1 must match mat2 dim 0

dipam7 commented 4 years ago

Were you able to solve this? I am getting the same error

joonson commented 4 years ago

If your video file is not 224x224 at 25 fps, you will need to run run_pipeline.py first.

QUTGXX commented 3 years ago

If your video file is not 224x224 at 25 fps, you will need to run run_pipeline.py first.

Hi, I got the same error. And I have run the 'run_pipeline.py' and it produces many results including pyavi, pycrop, pyframes, pytemp and pywork. Could you please tell me what is it? And after this step, What I should do?

avisekiit commented 3 years ago

Thanks. Closing this now.

Unmesh28 commented 2 years ago

@avisekiit I am facing similar issue. How did you resolve it ?

ThetaRgo commented 1 year ago

And I have run the 'run_pipeline.py' and it produces many results including pyavi, pycrop, pyframes, pytemp and pywork. Could you please tell me what is it? And after this step, What I should do?

hello,bug not solved,i have run_pipeline.py first and use the result avi files in pyavis folder to run demo,but get the same error