This repository has been archived by the owner on Nov 17, 2023. It is now read-only.
[example]add bucketing/batchnorm and improved performance for speech_recognition example #6971
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
|
@piiswrong I tested on latest build and it works well. Please let me know if there is something to do. |
Soonhwan-Kwon
changed the title
|
Thanks. LGTM |
Guneet-Dhillon
pushed a commit
to Guneet-Dhillon/mxnet
that referenced
this pull request
Sep 13, 2017
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Outdated suggestions cannot be applied.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.
add bucketing and batch norm scheme for speech_recognition example to improve training performance
add flexibility to support various optimizer
fix bug in generating bi-graphemes dictionray
add option not to save csv file to improve performane and reduce disk space requirement
and it solves performance issue(speed) related to #6418
and may related to issues #3076, #6115, #2663
when using both bucketing(variable length) and batch norm
although it is not a solution for time-step wise but layer wise approach for batch normalization