RuntimeError: result type Float can't be cast to the desired output type Long

[turian]

Just as a sanity check, I tried running this on a CPU machine. But with both fftnet_config.json and wavenet_config.json it crashes with the following error. This also happens with GPUs on Google Colab

Warning: There's no GPU available on this machine, training will be performed on CPU.
Train Step: [2/10000 (0%)] Loss: 5.568979
Traceback (most recent call last):
  File "train.py", line 71, in <module>
    main(config, args.resume)
  File "train.py", line 44, in main
    trainer.train()
  File "/Users/personal/dev/wavenet-like-vocoder/trainer/trainer.py", line 47, in train
    self.writer.add_image('input', make_grid(data.cpu(), nrow=8, normalize=True))
  File "/usr/local/lib/python3.7/site-packages/torchvision/utils.py", line 67, in make_grid
    norm_range(tensor, range)
  File "/usr/local/lib/python3.7/site-packages/torchvision/utils.py", line 61, in norm_range
    norm_ip(t, float(t.min()), float(t.max()))
  File "/usr/local/lib/python3.7/site-packages/torchvision/utils.py", line 55, in norm_ip
    img.add_(-min).div_(max - min + 1e-5)
RuntimeError: result type Float can't be cast to the desired output type Long

[yoyolicoris]

@turian thanks for your report.
Seems there has been some changes in newer version torchvision.
Please change data.cpu() to condition.cpu() in the following line, should fix the problem.
https://github.com/yoyololicon/wavenet-like-vocoder/blob/3591786b6507173323b7b657a98b9bdffabbee46/trainer/trainer.py#L47