hub / github.com/alibaba/nann / _ctc_state_trans

Function _ctc_state_trans

tensorflow/tensorflow/python/ops/ctc_ops.py:372–425 · view source on GitHub ↗

Compute CTC alignment model transition matrix. Args: label_seq: tensor of shape [batch_size, max_seq_length] Returns: tensor of shape [batch_size, states, states] with a state transition matrix computed for each sequence of the batch.

(label_seq)

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers 1

ctc_loss_and_gradFunction · 0.85

Calls 10

onesMethod · 0.80

tileMethod · 0.80

_get_dimFunction · 0.70

name_scopeMethod · 0.45

rangeMethod · 0.45

stackMethod · 0.45

concatMethod · 0.45

scatter_ndMethod · 0.45

expand_dimsMethod · 0.45

castMethod · 0.45

Tested by

no test coverage detected