tf.nn.ctc_beam_search_decoder | TensorFlow v2.16.1 (original) (raw)

tf.nn.ctc_beam_search_decoder

Stay organized with collections Save and categorize content based on your preferences.

Performs beam search decoding on the logits given in input.

Compat aliases for migration

tf.compat.v1.nn.ctc_beam_search_decoder_v2

tf.nn.ctc_beam_search_decoder(
    inputs, sequence_length, beam_width=100, top_paths=1
)

Args
inputs	3-D float Tensor, size [max_time, batch_size, num_classes]. The logits.
sequence_length	1-D int32 vector containing sequence lengths, having size[batch_size].
beam_width	An int scalar >= 0 (beam search beam width).
top_paths	An int scalar >= 0, <= beam_width (controls output size).

Returns
A tuple (decoded, log_probabilities) where
decoded	A list of length top_paths, where decoded[j]is a SparseTensor containing the decoded outputs:decoded[j].indices: Indices matrix [total_decoded_outputs[j], 2]; The rows store: [batch, time]. decoded[j].values: Values vector, size [total_decoded_outputs[j]]. The vector stores the decoded classes for beam j. decoded[j].dense_shape: Shape vector, size (2). The shape values are: [batch_size, max_decoded_length[j]].
log_probability	A float matrix [batch_size, top_paths] containing sequence log-probabilities.

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates. Some content is licensed under the numpy license.

Last updated 2024-04-26 UTC.