Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Connectionist Temporal Classification Ops Fix #40012

Merged
merged 1 commit into from Jun 2, 2020
Merged

Connectionist Temporal Classification Ops Fix #40012

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
12 changes: 6 additions & 6 deletions tensorflow/python/ops/ctc_ops.py
View file
Open in desktop
Expand Up @@ -55,7 +55,7 @@ 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:

Expand Down Expand Up @@ -153,7 +153,7 @@ 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))
"""
# The second, third, etc output tensors contain the gradients. We use it in
Expand Down Expand Up @@ -608,7 +608,7 @@ 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:

Expand Down Expand Up @@ -648,7 +648,7 @@ 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):
Expand Down Expand Up @@ -701,7 +701,7 @@ 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:
Expand Down Expand Up @@ -748,7 +748,7 @@ 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:
Expand Down