experiments/STT-tensorflow
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Merge pull request from kyscg:ctc

Browse Source 
PiperOrigin-RevId: 314374155
Change-Id: Ic33bf9de0d6411ca67fe3fa6365e2e7504189f81
This commit is contained in:
TensorFlower Gardener 2020-06-02 11:55:24 -07:00
commit 28ca5613b6
1 changed files with 6 additions and 6 deletions

12
tensorflow/python/ops/ctc_ops.py
View File

@ -82,7 +82,7 @@ def ctc_loss(labels,
logits=None):
"""Computes the CTC (Connectionist Temporal Classification) Loss.
This op implements the CTC loss as presented in (Graves et al., 2016).
This op implements the CTC loss as presented in (Graves et al., 2006).
Input requirements:
@ -180,7 +180,7 @@ def ctc_loss(labels,
References:
Connectionist Temporal Classification - Labeling Unsegmented Sequence Data
with Recurrent Neural Networks:
[Graves et al., 2016](https://dl.acm.org/citation.cfm?id=1143891)
[Graves et al., 2006](https://dl.acm.org/citation.cfm?id=1143891)
([pdf](http://www.cs.toronto.edu/~graves/icml_2006.pdf))
"""
return _ctc_loss_impl(
@ -747,7 +747,7 @@ def ctc_loss_v2(labels,
name=None):
"""Computes CTC (Connectionist Temporal Classification) loss.
This op implements the CTC loss as presented in (Graves et al., 2016).
This op implements the CTC loss as presented in (Graves et al., 2006).
Notes:
@ -787,7 +787,7 @@ def ctc_loss_v2(labels,
References:
Connectionist Temporal Classification - Labeling Unsegmented Sequence Data
with Recurrent Neural Networks:
[Graves et al., 2016](https://dl.acm.org/citation.cfm?id=1143891)
[Graves et al., 2006](https://dl.acm.org/citation.cfm?id=1143891)
([pdf](http://www.cs.toronto.edu/~graves/icml_2006.pdf))
"""
if isinstance(labels, sparse_tensor.SparseTensor):
@ -946,7 +946,7 @@ def ctc_loss_dense(labels,
name=None):
"""Computes CTC (Connectionist Temporal Classification) loss.
This op implements the CTC loss as presented in (Graves et al., 2016),
This op implements the CTC loss as presented in (Graves et al., 2006),
using the batched forward backward algorithm described in (Sim et al., 2017).
Notes:
@ -993,7 +993,7 @@ def ctc_loss_dense(labels,
References:
Connectionist Temporal Classification - Labeling Unsegmented Sequence Data
with Recurrent Neural Networks:
[Graves et al., 2016](https://dl.acm.org/citation.cfm?id=1143891)
[Graves et al., 2006](https://dl.acm.org/citation.cfm?id=1143891)
([pdf](http://www.cs.toronto.edu/~graves/icml_2006.pdf))
Improving the efficiency of forward-backward algorithm using batched
computation in TensorFlow: