espnet2.legacy.nets.pytorch_backend.nets_utils.pad_list

source

espnet2.legacy.nets.pytorch_backend.nets_utils.pad_list(xs, pad_value)

Perform padding for the list of tensors.

• Parameters:
  • xs (List) – List of Tensors [(T_1, *), (T_2, *), …, (T_B, *)].
  • pad_value (float) – Value for padding.
• Returns: Padded tensor (B, Tmax, *).
• Return type: Tensor

Examples

>>> x = [torch.ones(4), torch.ones(2), torch.ones(1)]
>>> x
[tensor([1., 1., 1., 1.]), tensor([1., 1.]), tensor([1.])]
>>> pad_list(x, 0)
tensor([[1., 1., 1., 1.],
        [1., 1., 0., 0.],
        [1., 0., 0., 0.]])