Script 'mail_helper' called by obssrc Hello community, here is the log from the commit of package armnn for openSUSE:Factory checked in at 2021-01-25 18:24:32 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Comparing /work/SRC/openSUSE:Factory/armnn (Old) and /work/SRC/openSUSE:Factory/.armnn.new.28504 (New) ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Package is "armnn" Mon Jan 25 18:24:32 2021 rev:13 rq:866498 version:20.11 Changes: -------- --- /work/SRC/openSUSE:Factory/armnn/armnn.changes 2021-01-10 19:40:01.965567237 +0100 +++ /work/SRC/openSUSE:Factory/.armnn.new.28504/armnn.changes 2021-01-25 18:25:03.612554224 +0100 @@ -1,0 +2,7 @@ +Mon Jan 25 08:21:39 UTC 2021 - Guillaume GARDET <guillaume.gar...@opensuse.org> + +- Backport patch to fix tflite parser when built against + tensorflow 2.4: + * 96beb97.diff + +------------------------------------------------------------------- New: ---- 96beb97.diff ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Other differences: ------------------ ++++++ armnn.spec ++++++ --- /var/tmp/diff_new_pack.r2TtMQ/_old 2021-01-25 18:25:04.388555352 +0100 +++ /var/tmp/diff_new_pack.r2TtMQ/_new 2021-01-25 18:25:04.388555352 +0100 @@ -1,7 +1,7 @@ # # spec file for package armnn # -# Copyright (c) 2020 SUSE LLC +# Copyright (c) 2021 SUSE LLC # # All modifications and additions to the file contributed by third parties # remain the property of their copyright owners, unless otherwise agreed @@ -90,6 +90,8 @@ URL: https://developer.arm.com/products/processors/machine-learning/arm-nn Source0: https://github.com/ARM-software/armnn/archive/v%{version}.tar.gz#/armnn-%{version}.tar.gz Source1: armnn-rpmlintrc +# PATCH-FIX-UPSTREAM - https://github.com/ARM-software/armnn/issues/499 +Patch1: 96beb97.diff # PATCHES to add downstream ArmnnExamples binary - https://layers.openembedded.org/layerindex/recipe/87610/ Patch200: 0003-add-more-test-command-line-arguments.patch Patch201: 0005-add-armnn-mobilenet-test-example.patch @@ -424,6 +426,7 @@ %prep %setup -q -n armnn-%{version} +%patch1 -p1 %if %{with armnn_extra_tests} %patch200 -p1 %patch201 -p1 ++++++ 96beb97.diff ++++++ >From 96beb97f0ce6650d64fb15d9c920d70a1572672c Mon Sep 17 00:00:00 2001 From: Keith Mok <ek9...@gmail.com> Date: Thu, 07 Jan 2021 17:24:58 -0800 Subject: [PATCH] Adopt the change of tflite builtin code This fixes tflite parser cannot parse model with new schema Tensorflow 2.4 updated the schema to version 3. And breaks armnn tensorflow lite parser. Adopt changes to fix it. But it will require using Tensorflow 2.4+ schema_generated.h Signed-off-by: Keith Mok <ek9...@gmail.com> Change-Id: I9eed8542e0882a39b7799a4e870ad09c69c7808f --- diff --git a/src/armnnTfLiteParser/TfLiteParser.cpp b/src/armnnTfLiteParser/TfLiteParser.cpp index 8e0fae6..183e337 100644 --- a/src/armnnTfLiteParser/TfLiteParser.cpp +++ b/src/armnnTfLiteParser/TfLiteParser.cpp @@ -645,7 +645,8 @@ for (OperatorPtr const& op : subgraph->operators) { auto const& opCodePtr = m_Model->operator_codes[op->opcode_index]; - auto builtinCode = opCodePtr->builtin_code; + auto builtinCode = std::max(opCodePtr->builtin_code, + static_cast<tflite::BuiltinOperator>(opCodePtr->deprecated_builtin_code)); if (builtinCode > tflite::BuiltinOperator_MAX) { @@ -765,7 +766,8 @@ const auto & operatorPtr = m_Model->subgraphs[subgraphIndex]->operators[operatorIndex]; auto opcodeIndex = operatorPtr->opcode_index; - auto opcode = m_Model->operator_codes[opcodeIndex]->builtin_code; + auto opcode = std::max(m_Model->operator_codes[opcodeIndex]->builtin_code, + static_cast<tflite::BuiltinOperator>(m_Model->operator_codes[opcodeIndex]->deprecated_builtin_code)); if (!m_Options || !m_Options.value().m_StandInLayerForUnsupported) {
