Closed TheIllusion closed 7 years ago
sergeytulyakov
commented
7 years ago Hi,
Could you change
generator = torch.load(args["<model>"], map_location={'cuda:0': 'cpu'})
to
generator = torch.load(args["<model>"])
and see if it works?
It looks like some of the tensors are in gpu, but some are in cpu.
TheIllusion
commented
7 years ago Thanks a lot for you quick reply. I think I'm almost there.
Sorry for another dumb question...
I'm encountering the following new problem...
Could you guide me to avoid this?
sergeytulyakov
commented
7 years ago It looks like the issues is with ffmpeg. If you change
pipe = sp.Popen(command, stdin=sp.PIPE, stderr=sp.PIPE)
to
pipe = sp.Popen(command, stdin=sp.PIPE)
you will be able to see more details about the error
TheIllusion
commented
7 years ago Thanks a lot!
ShibaPrasad
commented
7 years ago Hi TheIllusion,
Are you able to execute the code? I am not using docker as suggested. Using Python 3.6 and on ubuntu command prompt. Also opened an issue.
vipulbjj
commented
6 years ago After doing the ffmpeg thing as told by you, I'm getting this error
Attached screenshot of the error https://drive.google.com/file/d/13AuoobWDDfAEC4yNQQpiRVllvu-NRjwt/view?usp=sharing @sergeytulyakov Please help.
PhoebeWangintw
commented
5 years ago After doing the ffmpeg thing as told by you, I'm getting this error
Attached screenshot of the error https://drive.google.com/file/d/13AuoobWDDfAEC4yNQQpiRVllvu-NRjwt/view?usp=sharing @sergeytulyakov Please help.
I know this might be late, but I hope it can still help others. For python3, modify
pipe = sp.Popen(command, stdin=sp.PIPE, stderr=sp.PIPE)to
pipe = sp.Popen(command, stdin=sp.PIPE)as stated by @sergeytulyakov And modify stdin.write to
pipe.communicate(video.tostring())This fixed the broken pipe problem. Reference from this gist.
Dear the author of MocoGAN:
I am deeply impressed about your fantastic work. And I really appreciate that you've opened the source code of this project.
I have a small problem when using generate_video.py file. After I trained the model and run,
"python generate_videos.py --num_videos 10 --output_format gif --number_of_frames 16 ../logs/actions/generator_21700.pytorch output"
The following error occurrs:
Traceback (most recent call last): File "generatevideos.py", line 61, in
v, = generator.sample_videos(1, int(args['--number_of_frames']))
File "/mocogan/src/models.py", line 268, in sample_videos
z, z_category_labels = self.sample_z_video(num_samples, video_len)
File "/mocogan/src/models.py", line 259, in sample_z_video
z_motion = self.sample_z_m(num_samples, video_len)
File "/mocogan/src/models.py", line 224, in sample_z_m
h_t.append(self.recurrent(e_t, h_t[-1]))
File "/usr/local/lib/python2.7/dist-packages/torch/nn/modules/module.py", line 224, in call
result = self.forward(*input, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/torch/nn/modules/rnn.py", line 682, in forward
self.bias_ih, self.bias_hh,
File "/usr/local/lib/python2.7/dist-packages/torch/nn/_functions/rnn.py", line 49, in GRUCell
gi = F.linear(input, w_ih)
File "/usr/local/lib/python2.7/dist-packages/torch/nn/functional.py", line 555, in linear
output = input.matmul(weight.t())
File "/usr/local/lib/python2.7/dist-packages/torch/autograd/variable.py", line 560, in matmul
return torch.matmul(self, other)
File "/usr/local/lib/python2.7/dist-packages/torch/functional.py", line 173, in matmul
return torch.mm(tensor1, tensor2)
File "/usr/local/lib/python2.7/dist-packages/torch/autograd/variable.py", line 579, in mm
return Addmm.apply(output, self, matrix, 0, 1, True)
File "/usr/local/lib/python2.7/dist-packages/torch/autograd/_functions/blas.py", line 26, in forward
matrix1, matrix2, out=output)
TypeError: torch.addmm received an invalid combination of arguments - got (int, torch.cuda.FloatTensor, int, torch.cuda.FloatTensor, torch.FloatTensor, out=torch.cuda.FloatTensor), but expected one of:
(float beta, torch.cuda.FloatTensor source, float alpha, torch.cuda.sparse.FloatTensor mat1, torch.cuda.FloatTensor mat2, *, torch.cuda.FloatTensor out) didn't match because some of the arguments have invalid types: (int, torch.cuda.FloatTensor, int, torch.cuda.FloatTensor, torch.FloatTensor, out=torch.cuda.FloatTensor)
I think there must be some mistakes I made, but could you look into it give me any clue?