After training 1 epoch, train_first.py crashes: RuntimeError: Expected 2D (unbatched) or 3D (batched) input to conv1d, but got input of size: [1, 1, 1, 800]

[fungus75]

I tried out to train with the default settings on a 3090 (LJ-Speech dataset from https://keithito.com/LJ-Speech-Dataset/,... all like shown in the readme)

I only had to adjust config.yml to fit into my 3090: batch_size: 16 max_len: 150

Others defaut.

After 1 epoch the script crashes (maybe during validation?)

Traceback (most recent call last):
  File "train_first.py", line 445, in <module>
    main()
  File "/home/ai/miniconda3/envs/StyleTTS/lib/python3.8/site-packages/click/core.py", line 1157, in __call__
    return self.main(*args, **kwargs)
  File "/home/ai/miniconda3/envs/StyleTTS/lib/python3.8/site-packages/click/core.py", line 1078, in main
    rv = self.invoke(ctx)
  File "/home/ai/miniconda3/envs/StyleTTS/lib/python3.8/site-packages/click/core.py", line 1434, in invoke
    return ctx.invoke(self.callback, **ctx.params)
  File "/home/ai/miniconda3/envs/StyleTTS/lib/python3.8/site-packages/click/core.py", line 783, in invoke
    return __callback(*args, **kwargs)
  File "train_first.py", line 407, in main
    y_rec = model.decoder(en, F0_real, real_norm, s)
  File "/home/ai/miniconda3/envs/StyleTTS/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/home/ai/miniconda3/envs/StyleTTS/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
    return forward_call(*args, **kwargs)
  File "/data/ai/StyleTTS2/Modules/istftnet.py", line 511, in forward
    F0 = self.F0_conv(F0_curve.unsqueeze(1))
  File "/home/ai/miniconda3/envs/StyleTTS/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/home/ai/miniconda3/envs/StyleTTS/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1582, in _call_impl
    result = forward_call(*args, **kwargs)
  File "/home/ai/miniconda3/envs/StyleTTS/lib/python3.8/site-packages/torch/nn/modules/conv.py", line 310, in forward
    return self._conv_forward(input, self.weight, self.bias)
  File "/home/ai/miniconda3/envs/StyleTTS/lib/python3.8/site-packages/torch/nn/modules/conv.py", line 306, in _conv_forward
    return F.conv1d(input, weight, bias, self.stride,
RuntimeError: Expected 2D (unbatched) or 3D (batched) input to conv1d, but got input of size: [1, 1, 1, 800]