Closed ajaysg-zz closed 5 years ago
@rafaelvalle please help
I faced the same issue today. Do you have any solution for that?
What is the dimension of the dummy_input you created?
it was like this:
mel_extra=torch.tensor(np.full((1,80,222),-10.0)).float()
dummy_input=torch.autograd.Variable(mel_extra).cuda().float()
waveglow_path = './waveglow_256channels.pt' waveglow = torch.load(waveglow_path)['model']
mel_extra=torch.tensor(np.full((1,80,222),-10.0)).float() dummy_input=torch.autograd.Variable(mel_extra).cuda().float()
audio = torch.tensor(np.full((1,222), -0.5)).float() audio_input = torch.autograd.Variable(audio).cuda().float() torch.onnx.export(waveglow, ((dummy_input, audio_input),), "./waveglow.onnx")
It can start to run export, but since logdet operator is not supported, export failed.
/home/user/anaconda3/envs/pytts/lib/python3.6/site-packages/torch/onnx/utils.py:501: UserWarning: ONNX export failed on ATen operator logdet because torch.onnx.symbolic.logdet does not exist ...... RuntimeError: ONNX export failed: Couldn't export operator aten::logdet
@csapot Did you find any way to export the model to onnx format
@ajaysg no, finally I did not use this
@androidof2008 are you able to export to onnx
and the error is RuntimeError Traceback (most recent call last)