Port micro op GATHER_ND and its test code from lite #48812
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Outdated suggestions cannot be applied.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.
Issue #46268. This PR aims to finish porting GATHER_ND from TFL to TFLM.
(This PR combines the originally planned PRS 3, 4, and 5)
Notes:
1 For params/output tensors, only the float and int8_t data types are supported;
2 For indices tensors, only the int32_t data type is supported;
3 The reference implementation in lite/kernels/internal/reference/reference_ops.h was not used, due to the vector used in the reference (possible dynamic allocation);
4 As with the TFL kernel Gather_ND, the TFLM kernel does not yet support batch_dims as of April 23, 2021.