Tom Allsop

**System information** - TensorFlow version (you are using): 2.8 - Are you willing to contribute it (Yes/No): Yes **Motivation** This would be beneficial for models that use this layer -...

Implement mm op for Arm backend

2

* Add legalization from aten.mm to TOSA MatMul for FP32 & INT8 types * Add tests for main and base inference * Add an annotator for aten.mm in the quantizer

[TOSA] Fix tfl.transpose_conv legalization when layer has bias

20

This PR fixes the legalization of tfl.transpose_conv in the case where the layer has a non-zero bias.

Adding model stats to aot_arm_compiler

1

* Adds GenericModelEvaluator, which gathers metrics applicable to all models * Adds --evaluate option to enable gathering quantization metrics Signed-off-by: Tom Allsop Change-Id: Ia9b591841f188870fa5e62d0568169498301393d