Fix some issues in official tf.nn.topk() in lite #18896
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Outdated suggestions cannot be applied.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.
Not sure if Google is planning a breaking change. If not:
The topk_v2 implementation has its output values and indices in the opposite order.
Below is TensorFlow Python API behavior:
Output array types are not correctly propagated.
First output array name should not be appended with
":0"
because it is deliberately removed here.If
k
is provided at run time, two output arrays will be dynamic, and have shape [..., 0] here. I changed toco to only check constant buffers instead, RFC.