MCPcopy Create free account
hub / github.com/alibaba/nann / ctc_state_log_probs

Function ctc_state_log_probs

tensorflow/tensorflow/python/ops/ctc_ops.py:428–465  ·  view source on GitHub ↗

Computes CTC alignment initial and final state log probabilities. Create the initial/final state values directly as log values to avoid having to take a float64 log on tpu (which does not exist). Args: seq_lengths: int tensor of shape [batch_size], seq lengths in the batch. max_seq_l

(seq_lengths, max_seq_length)

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 6

onesMethod · 0.80
reshapeMethod · 0.80
transposeMethod · 0.80
_get_dimFunction · 0.70
castMethod · 0.45
logMethod · 0.45

Tested by

no test coverage detected