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

Fix equation of sequence_softmax_op. #6810

Merged
merged 6 commits into from
Dec 21, 2017
Merged

Fix equation of sequence_softmax_op. #6810

Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
c81b9ec
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into…
wanghaoshuang Nov 28, 2017
ad47f91
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into…
wanghaoshuang Dec 13, 2017
020e0f7
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into…
wanghaoshuang Dec 18, 2017
a620e0c
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into…
wanghaoshuang Dec 20, 2017
98f9e57
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into…
wanghaoshuang Dec 21, 2017
befa7bb
Fix equation of sequence_softmax_op.
wanghaoshuang Dec 21, 2017
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 7 additions & 3 deletions paddle/operators/sequence_softmax_op.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,10 +50,14 @@ input Tensor can be either [N, 1] or [N], where N is the sum of the length
of all sequences.

The algorithm works as follows:

for i-th sequence in a mini-batch:
$$Out(X[lod[i]:lod[i+1]], :) =
\frac{\exp(X[lod[i]:lod[i+1], :])}
{\sum(\exp(X[lod[i]:lod[i+1], :]))}$$

$$
Out(X[lod[i]:lod[i+1]], :) = \
\frac{\exp(X[lod[i]:lod[i+1], :])} \
{\sum(\exp(X[lod[i]:lod[i+1], :]))}
$$

For example, for a mini-batch of 3 sequences with variable-length,
each containing 2, 3, 2 time-steps, the lod of which is [0, 2, 5, 7],
Expand Down