Fix bug in tf.keras.metrics.sparse_categorical_accuracy #22392
Merged
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Outdated suggestions cannot be applied.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_true
can be(num_samples, 1)
or(num_samples,)
, see #22190 for detail. The existing code assume the shape ofy_true
is(num_samples, 1)
, always reduce in the last dimension which leads the incorrect output. Actually we should check the shape ofy_true
and squeeze if applicable.Meanwhile, I also fix
sparse_top_k_categorical_accuracy
which has the same issue.