Add python API for Warp-CTC op #7438
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
qingqing01
reviewed
Jan 12, 2018
python/paddle/v2/fluid/layers/nn.py
Outdated
|
|
||
| def warpctc(input, label, blank=0, norm_by_times=False, **kwargs): | ||
| """ | ||
| An operator integrating the open source warp-ctc library |
There was a problem hiding this comment.
- warp-ctc library -> Warp-CTC library, and URL.
python/paddle/v2/fluid/layers/nn.py
Outdated
| """ | ||
| An operator integrating the open source warp-ctc library | ||
| to compute Connectionist Temporal Classification (CTC) loss. | ||
| It can be aliased as softmax with ctc, since a native softmax activation is |
python/paddle/v2/fluid/layers/nn.py
Outdated
| of variable-length sequence, which is a 2-D Tensor with LoD | ||
| information. It is of the shape [Lg, 1], where Lg is th sum of | ||
| all labels' length. | ||
| blank: (int, default: 0), the blank label of Connectionist |
There was a problem hiding this comment.
the blank label -> the blank label index
python/paddle/v2/fluid/layers/nn.py
Outdated
| Temporal Classification (CTC) loss, which is in the | ||
| half-opened interval [0, num_classes + 1). | ||
| norm_by_times: (bool, default: false), whether to | ||
| normalize the gradients by the number of time-step, |
There was a problem hiding this comment.
It seems there is no need to normalize the gradient since there is always a mean_op after the loss. Need to pay attention to this, when verifying the model.
qingqing01
previously approved these changes
Jan 17, 2018
wanghaoshuang
changed the title
qingqing01
approved these changes
Jan 18, 2018
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.