Training Error. Epoch 5.

[PetrochukM]

This is the stack trace:

Traceback (most recent call last):
  File "train.py", line 211, in <module>
    main()
  File "train.py", line 199, in main
    train(model, criterion, optimizer, epoch, train_losses)
  File "train.py", line 119, in train
    loss = criterion(output, target[0], target[1])
  File "/home/michael/.local/lib/python2.7/site-packages/torch/nn/modules/module.py", line 206, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/michael/Desktop/loop/model.py", line 42, in forward
    mask_ = mask.expand_as(input)
  File "/home/michael/.local/lib/python2.7/site-packages/torch/autograd/variable.py", line 655, in expand_as
    return Expand(tensor.size())(self)
  File "/home/michael/.local/lib/python2.7/site-packages/torch/autograd/_functions/tensor.py", line 115, in forward
    result = i.expand(*self.sizes)
RuntimeError: The expanded size of the tensor (21) must match the existing size (5) at               non-singleton dimension 0. at /b/wheel/pytorch-src/torch/lib/TH/THStorage.c:99

Any clue what is going on?

[PetrochukM]

Why are the target lengths:
loss = criterion(output, target[0], target[1])

Used to create a mask on the output:

        mask = self._sequence_mask(target[1]).unsqueeze(2)
        mask_ = mask.expand_as(input)

[PetrochukM]

Fixed this with:

class MaskedMSE(nn.Module):
    def __init__(self):
        super(MaskedMSE, self).__init__()
        self.criterion = nn.MSELoss(size_average=False)

    # Taken from
    # https://github.com/spro/practical-pytorch/blob/master/seq2seq-translation
    @staticmethod
    def _sequence_mask(sequence_length, max_len):
        batch_size = sequence_length.size(0)
        seq_range = torch.arange(0, max_len).long()
        seq_range_expand = seq_range.unsqueeze(0).expand(batch_size, max_len)
        seq_range_expand = Variable(seq_range_expand)
        if sequence_length.is_cuda:
            seq_range_expand = seq_range_expand.cuda()
        seq_length_expand = sequence_length.unsqueeze(1) \
                                           .expand_as(seq_range_expand)
        return (seq_range_expand < seq_length_expand).t().float()

    def forward(self, input, target, lengths):
        max_len = input.size(0)
        mask = self._sequence_mask(lengths, max_len).unsqueeze(2)
        mask_ = mask.expand_as(input)
        self.loss = self.criterion(input*mask_, target*mask_)
        self.loss = self.loss / mask.sum()
        return self.loss

[adampolyak]

Thanks!
Fixed in master.