Modified documentation for SparseCategoricalCrossentropy #34343
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
The documentation example for SparseCategoricalCrossentropy is mathematically inconsistent with a parallel example given for CategoricalCrossentropy and also is confusing. In particular the second element in the original SparseCategoricalCrossentropy example function call has component given by [.5, .89, .6] which is not normalized to be a probability (i.e. doesn't sum to 1.0). I modified it to be [.05, .89, .06] which does sum to 1.0 and also recomputed the loss to be 0.09458992, preserving all the precision from the function call. I hope this helps clarify things for users.
stmugisha
reviewed
Nov 20, 2019
There was a problem hiding this comment.
Could you try putting the usage example in doctest format as in this guide below? https://www.tensorflow.org/community/contribute/docs_ref
pavithrasv
approved these changes
Nov 20, 2019
tensorflow-bot
bot
added
kokoro:force-run
gbaned
added
ready to pull
|
@td2014 Can you please resolve conflicts? Thanks! |
gbaned
added
stat:awaiting response
tensorflowbutler
added
the
stale
|
It has been 14 days with no activity and the |
|
Closing this PR as the docs have been updated. |
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Outdated suggestions cannot be applied.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.
The documentation example for SparseCategoricalCrossentropy is mathematically inconsistent with a parallel example given for CategoricalCrossentropy and also is confusing. In particular the second element in the original SparseCategoricalCrossentropy example function call has component given by [.5, .89, .6] which is not normalized to be a probability (i.e. doesn't sum to 1.0). I modified it to be [.05, .89, .06] which does sum to 1.0 and also recomputed the loss to be 0.09458992, preserving all the precision from the function call. I hope this helps clarify things for users. Thanks.