https://gitcode.net/xusiwei1236/tflite-micro/-/commit/9dc65ef8ae8c2ea38f56e3a74ccf4356f6a8df58Port EMBEDDING_LOOKUP to TFLM (#1872)2023-05-29T01:25:28+00:00David Davisddavis-2015@users.noreply.github.com
@tensorflow/micro
Port the EMBEDDING_LOOKUP kernel operator to TFLM.
Recreate tests for kernel operator (INT8, FLOAT32).
Add SymmetricScaleFromMinMax method to test_helpers.h file.
Update Makefiles.
Update Bazel build script.
bug=fixes #1871https://gitcode.net/xusiwei1236/tflite-micro/-/commit/2b7f86c86ef15b6363efabf3e7163b3d478ea8b3Remove dead code from Dequantize (#2011)2023-05-31T02:01:17+00:00RJ Ascanirjascani@google.com
The Dequantize op only supports an output type of Float32. This change removes output_multiplier adjustments for Int32 outputs, as it cannot be reached due to an earlier check. It also eliminates logging for unsupported output types in DequantizeEval, as those would also be caught by an earlier check.
BUG=<a href="http://b/230890286" rel="nofollow noreferrer noopener" target="_blank">http://b/230890286</a>https://gitcode.net/xusiwei1236/tflite-micro/-/commit/78b4040c8a09798abedd557208b83f330217824dFix SELECT_V2 Prepare deallocation error (#2013)2023-06-01T03:28:11+00:00David Davisddavis-2015@users.noreply.github.com
@tensorflow/micro
Fix logic error in Prepare that prevented deallocation of temporary tensors, when scalars were present in the inputs.
Added 3 tests from TfLite for scalar inputs.
bug=fixes #2010https://gitcode.net/xusiwei1236/tflite-micro/-/commit/2b7a4ad621d0ff95db639bc98e39fb47d0363c21Update SELECT_V2 to match TFLM kernel code (#2015)2023-06-01T18:42:25+00:00David Davisddavis-2015@users.noreply.github.com
@tensorflow/micro
Eval method now uses TfLiteEvalTensor.
The `has_low_rank_input_condition` variable has been removed from OpData as SELECT_V2 does not use this variable.
All code outside of the registration has been placed into the anonymous namespace.
bug=fixes #2014