Fix bug in tf.keras.metrics.sparse_categorical_accuracy #22392
Merged
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
qlzh727
added
awaiting review
pavithrasv
approved these changes
Sep 21, 2018
4 tasks
qlzh727
added
awaiting testing (then merge)
ready to pull
|
I think the test failures are non-relevant. |
tensorflow-copybara
pushed a commit
that referenced
this pull request
Oct 4, 2018
PiperOrigin-RevId: 215760505
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Outdated suggestions cannot be applied.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.
Fix #22190
For the input of
tf.keras.metrics.sparse_categorical_accuracy, the shape ofy_truecan be(num_samples, 1)or(num_samples,), see #22190 for detail. The existing code assume the shape ofy_trueis(num_samples, 1), always reduce in the last dimension which leads the incorrect output. Actually we should check the shape ofy_trueand squeeze if applicable.Meanwhile, I also fix
sparse_top_k_categorical_accuracywhich has the same issue.