tf.nn.ctc_greedy_decoder

Performs greedy decoding on the logits given in input (best path).

tf.nn.ctc_greedy_decoder(
    inputs, sequence_length, merge_repeated=True, blank_index=None
)

Given a tensor as inputs, the blank_index parameter defines the class index of the blank symbol.

For example:

If blank_index is equal to 1:

inf = float("inf")
logits = tf.constant([[[   0., -inf, -inf],
                       [ -2.3, -inf, -0.1]],
                      [[ -inf, -0.5, -inf],
                       [ -inf, -inf, -0.1]],
                      [[ -inf, -inf, -inf],
                       [ -0.1, -inf, -2.3]]])
seq_lens = tf.constant([2, 3])
outputs = tf.nn.ctc_greedy_decoder(
    logits,
    seq_lens,
    blank_index=1)

Notes:

  • Regardless of the value of merge_repeated, if an index of a given time and batch corresponds to the blank_index, no new element is emitted.
  • Default blank_index is (num_classes - 1), unless overriden.

If merge_repeated is True, merge repeated classes in output. This means that if consecutive logits' maximum indices are the same, only the first of these is emitted. The sequence A B B * B * B (where '*' is the blank label) becomes

  • A B B B if merge_repeated=True.
  • A B B B B if merge_repeated=False.

inputs 3-D float Tensor sized [max_time, batch_size, num_classes]. The logits.
sequence_length 1-D int32 vector containing sequence lengths, having size [batch_size].
merge_repeated Boolean. Default: True.
blank_index (Optional). Default: num_classes - 1. Define the class index to use for the blank label. Negative values will start from num_classes, ie, -1 will reproduce the ctc_greedy_decoder behavior of using num_classes - 1 for the blank symbol, which corresponds to the default.

A tuple (decoded, neg_sum_logits) where
decoded A single-element list. decoded[0] is an SparseTensor containing the decoded outputs s.t.:

decoded.indices: Indices matrix (total_decoded_outputs, 2). The rows store: [batch, time].

decoded.values: Values vector, size (total_decoded_outputs). The vector stores the decoded classes.

decoded.dense_shape: Shape vector, size (2). The shape values are: [batch_size, max_decoded_length]

neg_sum_logits A float matrix (batch_size x 1) containing, for the sequence found, the negative of the sum of the greatest logit at each timeframe.