Fix SoftMax precision by utilizing double in the internal calculations - #3676
Merged
Conversation
Codecov Report
@@ Coverage Diff @@
## master #3676 +/- ##
==========================================
+ Coverage 72.77% 72.77% +<.01%
==========================================
Files 808 808
Lines 145588 145589 +1
Branches 16250 16250
==========================================
+ Hits 105956 105958 +2
Misses 35207 35207
+ Partials 4425 4424 -1
|
zeahmed
approved these changes
May 9, 2019
* Brew install libomp 7.0.0 only. * Brew install libomp 7.0.0 only. * Brew install libomp 7.0.0 only. * Brew install libomp 7.0.0 only.
This file contains hidden or 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes #3648
Uses
doublewhen calculating softmax exponent scores and only cast tofloatat the final step returning the probabilities.cc: @rauhs