From 28f177c45cb8e23b86c9f3ff435921183340fc33 Mon Sep 17 00:00:00 2001 From: Matthew Sloyan Date: Fri, 9 Apr 2021 14:38:52 +0100 Subject: IVGCVSW-5804 TfLiteParser fails to correctly parse ArgMinMax * Fix for GitHub#523. * Updated ParseArgMinMax function to read correct axis data. * Improved validation in ParseArgMinMax function. * Added ARG_MIN support to TfLiteParser. * Added ArgMinMax unit tests for TfLiteParser. Signed-off-by: Matthew Sloyan Change-Id: Ib4ce1a7c66e210c47859a130c4896aac958f2654 --- docs/01_01_parsers.dox | 2 ++ 1 file changed, 2 insertions(+) (limited to 'docs') diff --git a/docs/01_01_parsers.dox b/docs/01_01_parsers.dox index ae49303876..05e1225f93 100644 --- a/docs/01_01_parsers.dox +++ b/docs/01_01_parsers.dox @@ -158,6 +158,8 @@ This reference guide provides a list of TensorFlow Lite operators the Arm NN SDK The Arm NN SDK TensorFlow Lite parser currently supports the following operators: - ADD +- ARG_MAX +_ ARG_MIN - AVERAGE_POOL_2D, Supported Fused Activation: RELU , RELU6 , TANH, NONE - BATCH_TO_SPACE - CONCATENATION, Supported Fused Activation: RELU , RELU6 , TANH, NONE -- cgit v1.2.1