RuntimeError: Expected tensor for argument #1 'indices' to have scalar type Long; but got CUDAIntTensor instead about pytorch-dc-tts

[Joee1995]

environment: cuda-9.0 + cudnn-7.3.1 + python-3.6.7 + torch-0.4.0

[tugstugi]

@Joee1995 It is working under Linux/Anaconda/Cuda10/PyTorch1. Maybe it is a windows problem?

I made a Colab notebook: https://colab.research.google.com/drive/1aG_2uDK-sCWkHIReRqm8WW3y8XsI3Ltm

You can follow the commands in the above notebook to replicate an environment which can successfully train DC-TTS.

[Joee1995]

Really a windows problem.

When running in Linux, it works well at first, but there is another error at epoch 18:

epoch 18 with lr=1.22e-03
50%|██████████▌ | 1728/3456 [00:27<00:26, 66.45audios/s, l1=0.18589, att=0.00016]Traceback (most recent call last):
File "train-text2mel.py", line 157, in
train_epoch_loss = train(epoch, phase='train')
File "train-text2mel.py", line 140, in train
{'mels-true': S[0, :, :], 'mels-pred': Y[0, :, :], 'attention': A[0, :, :]})
File "/home/yy/TTS/pytorch-dc-tts/logger.py", line 29, in log_step
self.writer.add_image('%s/%s' % (self.model_name, key), image_dict[key], step)
File "/home/yy/anaconda3/envs/ptPy36/lib/python3.6/site-packages/tensorboardX/writer.py", line 427, in add_image
image(tag, img_tensor, dataformats=dataformats), global_step, walltime)
File "/home/yy/anaconda3/envs/ptPy36/lib/python3.6/site-packages/tensorboardX/summary.py", line 211, in image
tensor = convert_to_HWC(tensor, dataformats)
File "/home/yy/anaconda3/envs/ptPy36/lib/python3.6/site-packages/tensorboardX/utils.py", line 98, in convert_to_HWC
assert(len(tensor.shape) == len(input_format)), "size of input tensor and input format are different"
AssertionError: size of input tensor and input format are different

Thx!

[tugstugi]

Latest TensorboardX version behaves differently. Should be now fixed with 653fd14

[b29b]

@Joee1995 were you able to get it to run in windows later? would be great if anynone can get it to work in windows