metric

levenshtein_distance

Overview:

Levenshtein Distance, i.e. Edit Distance.

Arguments:

• pred (torch.LongTensor): shape: (N1, ) (N1 >= 0)

• target (torch.LongTensor): shape: (N2, ) (N2 >= 0)

• pred_extra (Optional[torch.Tensor])

• target_extra (Optional[torch.Tensor])

• extra_fn (Optional[Callable]): if specified, the distance metric of the extra input data

Returns:

• distance (torch.FloatTensor): distance(scalar), shape: (1, )

hamming_distance

Overview:

Hamming Distance

Arguments:

• pred (torch.LongTensor): pred input, boolean vector(0 or 1)

• target (torch.LongTensor): target input, boolean vector(0 or 1)

• weight (torch.LongTensor): weight to multiply

Returns:

• distance(torch.LongTensor): distance(scalar), shape (1, )

Shapes:

• pred & target (torch.LongTensor): shape \((B, N)\),

  while B is the batch size, N is the dimension