speech_synthesis.py", line 115 ,z = torch.cat((z, x), dim=2), Got 239 and 241 in dimension 1
Zhengyan-Sheng opened this issue · comments
Zhengyan-Sheng commented
Hello
I have run "python train.py --hparams magnus -d grid --filelist k-s01 -v"
But got:
…… ……
File "/home/zysheng/xts-master/models/speech_synthesis.py", line 115, in forward
z = torch.cat((z, x), dim=2)
RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 2. Got 239 and 241 in dimension 1 at /opt/conda/conda-bld/pytorch_1579022060824/work/aten/src/THC/generic/THCTensorMath.cu:71
This is wrong with the input or the code?
Zhengyan-Sheng commented
I had solved it. The hyperparameters of ' len-out' should be set 241.