nnf_ctc_loss: Ctc_loss

Description Usage Arguments

View source: R/nnf-loss.R

Description

The Connectionist Temporal Classification loss.

Usage

1
2
3
4
5
6
7
8
9
nnf_ctc_loss(
  log_probs,
  targets,
  input_lengths,
  target_lengths,
  blank = 0,
  reduction = c("mean", "sum", "none"),
  zero_infinity = FALSE
)

Arguments

log_probs

(T, N, C) where C = number of characters in alphabet including blank, T = input length, and N = batch size. The logarithmized probabilities of the outputs (e.g. obtained with nnf_log_softmax).

targets

(N, S) or (sum(target_lengths)). Targets cannot be blank. In the second form, the targets are assumed to be concatenated.

input_lengths

(N). Lengths of the inputs (must each be ≤q T)

target_lengths

(N). Lengths of the targets

blank

(int, optional) Blank label. Default 0.

reduction

(string, optional) – Specifies the reduction to apply to the output: 'none' | 'mean' | 'sum'. 'none': no reduction will be applied, 'mean': the sum of the output will be divided by the number of elements in the output, 'sum': the output will be summed. Default: 'mean'

zero_infinity

(bool, optional) Whether to zero infinite losses and the associated gradients. Default: FALSE Infinite losses mainly occur when the inputs are too short to be aligned to the targets.


torch documentation built on Oct. 7, 2021, 9:22 a.m.