This repository has been archived by the owner on Nov 22, 2022. It is now read-only.
RNNG: add tok/beam size to forward params #434
Closed
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
facebook-github-bot
added
the
CLA Signed
seayoung1112
force-pushed
the
export-D14718588
branch
3 times, most recently
from
6fa1ab2
to
4a0daf3
Compare
seayoung1112
added a commit
to seayoung1112/pytext-1
that referenced
this pull request
Apr 3, 2019
Summary: Pull Request resolved: facebookresearch#434 1 add tok/beam size to forward params 2 change the way of getting input from using enum to incrementing index, because the enum way is wrong when dict feat is optional and contextual feat is given (input position changed) 3 this change is backward compatible, but not forward compatible (old model will work with this code but new model will not work with existing predictor) Differential Revision: D14718588 fbshipit-source-id: 02aa8599809fed1feb6618d4014ca28d2aa04bf9
seayoung1112
force-pushed
the
export-D14718588
branch
from
4a0daf3
to
178d9a4
Compare
seayoung1112
added a commit
to seayoung1112/pytext-1
that referenced
this pull request
Apr 4, 2019
Summary: Pull Request resolved: facebookresearch#434 1 add tok/beam size to forward params 2 change the way of getting input from using enum to incrementing index, because the enum way is wrong when dict feat is optional and contextual feat is given (input position changed) 3 this change is backward compatible, but not forward compatible (old model will work with this code but new model will not work with existing predictor) Differential Revision: D14718588 fbshipit-source-id: 2289c97840a3e77d0a8f807f2d558be9b98da710
seayoung1112
force-pushed
the
export-D14718588
branch
from
178d9a4
to
1804b99
Compare
Summary: Pull Request resolved: facebookresearch#434 1 add tok/beam size to forward params 2 change the way of getting input from using enum to incrementing index, because the enum way is wrong when dict feat is optional and contextual feat is given (input position changed) 3 this change is backward compatible, but not forward compatible (old model will work with this code but new model will not work with existing predictor) Reviewed By: wowitsmrinal Differential Revision: D14718588 fbshipit-source-id: 1aaa763e20b4065d78ab425e4b50f1301452fbfe
seayoung1112
force-pushed
the
export-D14718588
branch
from
1804b99
to
8a1ebac
Compare
|
This pull request has been merged in 963cb9e. |
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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.
Summary:
1 add tok/beam size to forward params
2 change the way of getting input from using enum to incrementing index, because the enum way is wrong when dict feat is optional and contextual feat is given (input position changed)
3 this change is backward compatible, but not forward compatible (old model will work with this code but new model will not work with existing predictor)
Differential Revision: D14718588