platform/upstream/armnn.git
3 years agoCorrect TuningLevel enumeration values 57/263557/1 accepted/tizen_6.5_unified accepted/tizen_7.0_unified accepted/tizen_7.0_unified_hotfix tizen_6.5 tizen_7.0 tizen_7.0_hotfix accepted/tizen/6.5/unified/20211028.223402 accepted/tizen/7.0/unified/20221110.062033 accepted/tizen/7.0/unified/hotfix/20221116.110607 accepted/tizen/unified/20210909.101205 submit/tizen/20210906.093902 submit/tizen_6.5/20211028.163301 tizen_6.5.m2_release tizen_7.0_m2_release
Inki Dae [Tue, 16 Mar 2021 07:24:09 +0000 (16:24 +0900)]
Correct TuningLevel enumeration values

According to the header description - include/armnn/IRuntime.hpp, Each level should have below value.
-----------------------------------------------------------------------------------------------------
"TuningLevel" : int [0..3] (0=UseOnly(default) | 1=RapidTuning | 2=NormalTuning | 3=ExhaustiveTuning)
-----------------------------------------------------------------------------------------------------

And also src/backends/cl/ClBackendContext.cpp uses below enumeration values internally
for the tuning level,
----------------------
enum class TuningLevel
{
    None,
    Rapid,
    Normal,
    Exhaustive
};
----------------------

So this patch corrects TuningLevel enumeration values - which is exposed to user - to be consistent
with ones internally used.

This is upstream patch,
 https://review.mlplatform.org/c/ml/armnn/+/5269

Change-Id: I9a8aeea0115579bfd16cbe01f39183b96329cdfd
Signed-off-by: Inki Dae <inki.dae@samsung.com>
3 years agopackaging: Fix aarch64 build error 64/257264/1 accepted/tizen/unified/20210428.040451 submit/tizen/20210422.015846 submit/tizen/20210423.055448 submit/tizen/20210427.093759
Inki Dae [Thu, 22 Apr 2021 01:48:49 +0000 (10:48 +0900)]
packaging: Fix aarch64 build error

Change-Id: Ica83e9c26bdd588915710ae1efb80f7d3b93add0
Signed-off-by: Inki Dae <inki.dae@samsung.com>
3 years agotensorflow: update tflite schema files submit/tizen/20210421.062230
Inki Dae [Mon, 15 Mar 2021 09:27:36 +0000 (18:27 +0900)]
tensorflow: update tflite schema files

Change-Id: Id324bd8939376cd5d78fc8d8afe8ece6b1bed347
Signed-off-by: Inki Dae <inki.dae@samsung.com>
3 years agopackaging: use internal schema file and copy manifest file
Inki Dae [Mon, 15 Mar 2021 09:26:31 +0000 (18:26 +0900)]
packaging: use internal schema file and copy manifest file

Change-Id: I078dd3bc37737eb6ca57eb94e9485b5e9b77fdc1
Signed-off-by: Inki Dae <inki.dae@samsung.com>
3 years agopackaging: add xxd binary
Inki Dae [Thu, 2 Jul 2020 02:43:11 +0000 (11:43 +0900)]
packaging: add xxd binary

Change-Id: I1f7bf666b1e156405ad75c7962c1157b6bdaefff
Signed-off-by: Inki Dae <inki.dae@samsung.com>
3 years agoUse Tizen specific TF_LITE_SCHEMA_PATH
Inki Dae [Mon, 29 Jun 2020 09:25:07 +0000 (18:25 +0900)]
Use Tizen specific TF_LITE_SCHEMA_PATH

The schema file, schema.fbs, will be installed in /usr/share/...
in case of Tizen so use the specific TF_LITE_SCHEMA_PATH
so that ARMNN can find schema.fbs in given path.

Change-Id: Idd9b23000d18995fc5df4a45b0510c47231ae0c2
Signed-off-by: Inki Dae <inki.dae@samsung.com>
3 years agoFix pc file
Inki Dae [Mon, 29 Jun 2020 08:11:14 +0000 (17:11 +0900)]
Fix pc file

Change-Id: I57de41dcc1eab8867d2da23ec82527e6d6cac00e
Signed-off-by: Inki Dae <inki.dae@samsung.com>
3 years agopackaging: Install xxd binary
Inki Dae [Fri, 29 May 2020 05:36:25 +0000 (14:36 +0900)]
packaging: Install xxd binary

ARMNN needs xxd binary to dump a given file with hex type
when compiling.

Change-Id: I0802c3cd5749173d8856781b98573e8585add862
Signed-off-by: Inki Dae <inki.dae@samsung.com>
3 years agopackaging: modify version to 21.02
Inki Dae [Fri, 29 May 2020 00:34:01 +0000 (09:34 +0900)]
packaging: modify version to 21.02

Change-Id: Ica624cba77373eac73acb33f2dca311fed603f54
Signed-off-by: Inki Dae <inki.dae@samsung.com>
3 years agofix build error
Inki Dae [Thu, 28 May 2020 10:01:23 +0000 (19:01 +0900)]
fix build error

Change-Id: I2df41ef0d73282e477948eb0f57150b9f2727087
Signed-off-by: Inki Dae <inki.dae@samsung.com>
3 years agoDist/Tizen: support selective framework and pkgconfig
Parichay Kapoor [Tue, 31 Dec 2019 10:29:38 +0000 (19:29 +0900)]
Dist/Tizen: support selective framework and pkgconfig

Add package config for armnn package
Add selective enabling of framework in build
Add flatc while building with flatbuffers
Add tflite header files

Change-Id: I77eecd22cf80eb4c5ccfb2a83399354869dac39b
Signed-off-by: Parichay Kapoor <pk.kapoor@samsung.com>
3 years agoDist/Tizen: remove obsolete pkg names
MyungJoo Ham [Fri, 29 Nov 2019 03:57:25 +0000 (12:57 +0900)]
Dist/Tizen: remove obsolete pkg names

There is no one using that name.
Remove the obsolete name.

Change-Id: Ice9cc4fcace5fc6d08d7db396fee976f3615c467
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
3 years agoDist/Tizen: spec file clean-up
MyungJoo Ham [Tue, 26 Nov 2019 02:16:21 +0000 (11:16 +0900)]
Dist/Tizen: spec file clean-up

1. Do not use "release" postfix for the main library.
2. Do not use -n %{name} prefix. Drop that.
3. Added missing interanl dependencies

Change-Id: Ibb617be8206df149cd2849deef4fbc859484ebfc
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
3 years agopackaging: enable SHARED_BOOST flag
Inki Dae [Wed, 18 Dec 2019 06:28:36 +0000 (15:28 +0900)]
packaging: enable SHARED_BOOST flag

Change-Id: I444982b9b171a4b341b73bd8085255109c0c2a27
Signed-off-by: Inki Dae <inki.dae@samsung.com>
3 years agopackaging: clean up spec file
Inki Dae [Tue, 3 Dec 2019 05:33:47 +0000 (14:33 +0900)]
packaging: clean up spec file

Change-Id: If92810d16ceb38786fed8e66d8c03242ea6188f6
Signed-off-by: Inki Dae <inki.dae@samsung.com>
3 years agopackaging: install required packages
Inki Dae [Tue, 26 Nov 2019 10:23:57 +0000 (19:23 +0900)]
packaging: install required packages

Change-Id: I8e0677c0afc649fadc2299a52b75316c255e1bb7
Signed-off-by: Inki Dae <inki.dae@samsung.com>
3 years agoupdate tensorflow lite schema files
Inki Dae [Tue, 26 Nov 2019 10:23:34 +0000 (19:23 +0900)]
update tensorflow lite schema files

Change-Id: Ibc6639cf2c0ebe9c8d9ad09c8967a2286739d17a
Signed-off-by: Inki Dae <inki.dae@samsung.com>
3 years agopackaging: update spec file for acl v19.11 support
Inki Dae [Tue, 8 Oct 2019 05:35:01 +0000 (14:35 +0900)]
packaging: update spec file for acl v19.11 support

This patch updates the spec file for acl v19.11 support
and drops TF parser support because it needs latest protobuf,
>= 3.7.1

Change-Id: Ic067b032790a3b60fa6b359bead66c67c7bbde09
Signed-off-by: Inki Dae <inki.dae@samsung.com>
3 years agopackaging: correct armnn version
Inki Dae [Tue, 12 Mar 2019 02:03:37 +0000 (11:03 +0900)]
packaging: correct armnn version

Change-Id: If7d441f87cd893866800b2db12052d75a2e6ff8e
Signed-off-by: Inki Dae <inki.dae@samsung.com>
3 years agoadd tensorflow lite parser support
Inki Dae [Thu, 20 Dec 2018 08:27:59 +0000 (17:27 +0900)]
add tensorflow lite parser support

Change-Id: I26b101415ed11a89f8bffdb54e635df74e21110d
Signed-off-by: Inki Dae <inki.dae@samsung.com>
3 years agoadd TF parser support
Inki Dae [Tue, 18 Dec 2018 08:50:34 +0000 (17:50 +0900)]
add TF parser support

Change-Id: Iba09005cb6249f7411319fc7265bad500ceb57e2
Signed-off-by: Inki Dae <inki.dae@samsung.com>
3 years agopackaging: add UnitTests app to rpm package
Inki Dae [Thu, 13 Dec 2018 05:47:32 +0000 (14:47 +0900)]
packaging: add UnitTests app to rpm package

Change-Id: Ifcc58be6e83cc4478227fab1b1cf9df849dc7dae
Signed-off-by: Inki Dae <inki.dae@samsung.com>
3 years agopacking: keep same package name for arm and aarch64
Inki Dae [Thu, 6 Sep 2018 01:12:47 +0000 (10:12 +0900)]
packing: keep same package name for arm and aarch64

Change-Id: I2330fe154b500931462a438405093270600e873b
Signed-off-by: Inki Dae <inki.dae@samsung.com>
3 years agopackaging: do not pack debug files
Inki Dae [Wed, 4 Jul 2018 04:19:26 +0000 (13:19 +0900)]
packaging: do not pack debug files

Change-Id: I55aec155f624f19a5c9f64f72a671e0026084103
Signed-off-by: Inki Dae <inki.dae@samsung.com>
3 years agoFix a build error
biao716.wang [Tue, 3 Jul 2018 08:59:56 +0000 (16:59 +0800)]
Fix a build error

Fixed build error: Found '/home/abuild/rpmbuild/BUILDROOT/armnn-18.05-0.arm' in installed files; aborting
refined this patch
Change-Id: I91534256de2144d86b37d42f85bb367643348bce
Signed-off-by : biao716.wang <biao716.wang@samsung.com>

3 years agoexternal: add single-file public domain library
Inki Dae [Thu, 28 Jun 2018 11:10:40 +0000 (20:10 +0900)]
external: add single-file public domain library

Signed-off-by: Inki Dae <inki.dae@samsung.com>
3 years agotests: fix Tizen build
Inki Dae [Tue, 26 Nov 2019 08:40:29 +0000 (17:40 +0900)]
tests: fix Tizen build

This patch moves install directory of examples
to prevent gbs build from failed.

Change-Id: Ib5ef3d8025c0b4375c21df81b7434c405b07c6e1
Signed-off-by: Inki Dae <inki.dae@samsung.com>
3 years agotests: fix InferenceTestImage app build error
Inki Dae [Fri, 22 Jun 2018 09:20:00 +0000 (18:20 +0900)]
tests: fix InferenceTestImage app build error

Signed-off-by: Inki Dae <inki.dae@samsung.com>
3 years agopackaging: add spec file for Tizen build
Inki Dae [Thu, 28 Jun 2018 10:50:37 +0000 (19:50 +0900)]
packaging: add spec file for Tizen build

Signed-off-by: Inki Dae <inki.dae@samsung.com>
3 years agoMLCE-356 'Documentation issue on CrossCompilation guide'
Francis Murtagh [Mon, 22 Feb 2021 10:25:42 +0000 (10:25 +0000)]
MLCE-356 'Documentation issue on CrossCompilation guide'

* Add updates for Boost, Caffe and TF parsers
* Update path

Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: Ice9e5393ab47a678b5fe7c1ba4070460ef5b473c
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
3 years agoMinor doc updates
Nikhil Raj [Mon, 22 Feb 2021 14:40:39 +0000 (14:40 +0000)]
Minor doc updates

* Updating README
* Updating android ndk build guide

Change-Id: I09f5e4fe09d590b6b482800730b78cbc84cee9e9
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
3 years agoIVGCVSW-5695 Update supported operators
Jan Eilers [Fri, 19 Feb 2021 09:38:03 +0000 (09:38 +0000)]
IVGCVSW-5695 Update supported operators

 * Update supported operators for the delegate, parsers,
   serializer and deserializer

Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: I33ac99a29d894eec055cd05411014075d78b3168

3 years agoIVGCVSW-5682 Add Deprecation Notification
Jan Eilers [Thu, 18 Feb 2021 12:33:17 +0000 (12:33 +0000)]
IVGCVSW-5682 Add Deprecation Notification

 * For Quantizer, Tensorflow Parser and Caffe Parser

Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: If30daa54947c417c0d700f11e630546b1745b72e

3 years agoFix TransformIterator operator=
Rob Hughes [Thu, 18 Feb 2021 10:18:15 +0000 (10:18 +0000)]
Fix TransformIterator operator=

These two operator overloads were giving compile errors as they had
misspelled the names of the member variables.

Presumably they are not used in any of the code and not tested anywhere,
and so the compilers being used on the CI decided to not report this
error. I encountered this error using the MSVC compiler, but it may
cause problems on others too.

Change-Id: I200fc98dbd024d13dbf0e2eca2a0dcd2b0bef261
Signed-off-by: Rob Hughes <robert.hughes@arm.com>
3 years agoRemove unnecessary friend function
Rob Hughes [Thu, 18 Feb 2021 11:47:11 +0000 (11:47 +0000)]
Remove unnecessary friend function

IOptimizedNetwork declares a friend function (CreatePreCompiledWorkloadTest)
that is not necessary as that function does not use any of the non-public
members of the class. I suspect this is leftover after a refactor,
as the function in question uses GetGraphForTesting() to access the
internals instead.

This friend declaration was causing me a compilation error as the namespace
of the declared friend function did not match the namespace of the definition.
Removing it solves the compilation error and tidies up the code.

Change-Id: I4aa893cb5108cd3b72ca355f725fe7a0cd053a7e
Signed-off-by: Rob Hughes <robert.hughes@arm.com>
3 years agoIVGCVSW-5394 TfLiteDelegate: Implement the Lstm operator
Mike Kelly [Wed, 17 Feb 2021 13:45:50 +0000 (13:45 +0000)]
IVGCVSW-5394 TfLiteDelegate: Implement the Lstm operator

 * Add LSTM operator

Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: If8c667685fa1176738ffe2e6d08b1c684e7ee6b2

3 years agoIVGCVSW-5654 Fix failing float 16 delegate tests on android
Finn Williams [Wed, 17 Feb 2021 18:12:39 +0000 (18:12 +0000)]
IVGCVSW-5654 Fix failing float 16 delegate tests on android

 * add template specialization declaration to header to resolve clang issue

Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: Id8104d6feda19ed3f5f0cb018d719b1677772d9b

3 years agoIVGCVSW-5734 Building armnn failed in our Backends CI job
Francis Murtagh [Wed, 17 Feb 2021 11:01:00 +0000 (11:01 +0000)]
IVGCVSW-5734 Building armnn failed in our Backends CI job

 * CreateTestNetwork() and CreateTransposeTestNetwork should only be
   defined if Ref enabled; the same as the test its called in otherwise
   it's defined but not called.

Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: I7bc522a7884d216d1a8e51afd7cec7a66e4e2947

3 years agoIVGCVSW-5665 'Basic NN Driver support for next OS Version'
Sadik Armagan [Tue, 16 Feb 2021 10:44:05 +0000 (10:44 +0000)]
IVGCVSW-5665 'Basic NN Driver support for next OS Version'

Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: If69dbc230e2136def8a697ab25b9c4cb5cb8c731

3 years agoIVGCVSW-4873 Implement Pimpl Idiom for INetwork and IOptimizedNetwork
Francis Murtagh [Mon, 15 Feb 2021 18:23:17 +0000 (18:23 +0000)]
IVGCVSW-4873 Implement Pimpl Idiom for INetwork and IOptimizedNetwork

!android-nn-driver:5042

Signed-off-by: Kevin May <kevin.may@arm.com>
Change-Id: Ia1ce8b839e81b46428ba0f78463e085e5906958d
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
3 years agoRemove the undefined behaviour warning from InstallationViaAptRepository.md
Nikhil Raj [Mon, 15 Feb 2021 14:35:29 +0000 (14:35 +0000)]
Remove the undefined behaviour warning from InstallationViaAptRepository.md

Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ia85dea61a6c63cf6d2ec8c63d4ce7494e66fa1cb

3 years agoUpdate pinned version of ACL to 21.02 release branch
Nikhil Raj [Mon, 15 Feb 2021 12:10:57 +0000 (12:10 +0000)]
Update pinned version of ACL to 21.02 release branch

Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I1671a68b97815a224c89c3abe2f3944d97446c09

3 years agoIVGCVSW-5694 Update Major, Minor release versions
Nikhil Raj [Thu, 11 Feb 2021 17:39:47 +0000 (17:39 +0000)]
IVGCVSW-5694 Update Major, Minor release versions

   * Update Arm NN version in Version.hpp and all guides
   * Change Project Version in Doxyfile

Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I05ab20a1ae5d0376a641df68a5877f97e7609052

3 years agoIVGCVSW-5675 Implement Pimpl Idiom for IProfiler (lower priority)
Francis Murtagh [Mon, 15 Feb 2021 10:11:28 +0000 (10:11 +0000)]
IVGCVSW-5675 Implement Pimpl Idiom for IProfiler (lower priority)

Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: If716f5f4e9b5433586b8a939d326830482da2f74

3 years agoIVGCVSW-5686 Add GpuAcc MLGO tuning file configuration argument
Finn Williams [Thu, 11 Feb 2021 16:16:42 +0000 (16:16 +0000)]
IVGCVSW-5686 Add GpuAcc MLGO tuning file configuration argument

Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I3f320499c379162f9d1b00cc8816bd144cd7eee4

3 years agoIVGCVSW-5679 Failure to run the build instructions to build ArmNN using android ndk
Nikhil Raj [Thu, 11 Feb 2021 14:49:19 +0000 (14:49 +0000)]
IVGCVSW-5679 Failure to run the build instructions to build ArmNN using android ndk

   * Provide FLATBUFFERS_INCLUDE_PATH in GlobalConfig.cmake if ARMCOMPUTECL is enabled

Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Iabd5bb9b8a63970df9b7f485d07f8c1ee1a78560

3 years agoIVGCVSW-5386 TfLiteDelegate: Add Strided Slice operator
Jan Eilers [Wed, 3 Feb 2021 09:14:30 +0000 (09:14 +0000)]
IVGCVSW-5386 TfLiteDelegate: Add Strided Slice operator

Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: Icd87b1c54e1a5de84893882da30840a9097f6d84

3 years agoIVGCVSW-5648 Adding serializer support for m_DimensionsSpecificity
Colm Donelan [Fri, 12 Feb 2021 12:43:35 +0000 (12:43 +0000)]
IVGCVSW-5648 Adding serializer support for m_DimensionsSpecificity

The field m_DimensionsSpecificity in TensorShape was not being serialized
and deserialized following implementation of type 1 dynamic tensors.

* Update schema.
* Add to Serializer and Deserializer.

Signed-off-by: Colm Donelan <Colm.Donelan@arm.com>
Change-Id: I7ddbdaf54c8f4b988c6cb300f90ba848a94bdad0

3 years agoIVGCVSW-5685 Add CpuAcc specific configuration option numberOfThreads
Matthew Sloyan [Wed, 10 Feb 2021 16:50:53 +0000 (16:50 +0000)]
IVGCVSW-5685 Add CpuAcc specific configuration option numberOfThreads

 * Added ability to set number of threads used in CpuAcc backend
 * Enabled number-of-threads option in ExecuteNetwork
 * Added TfLiteDelegate ModelOptions test
 * Added unsigned int type to BackendOptions.hpp

Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: Ia576d4f45cbe5df3654bc730bb5ebd5181d82b5a

3 years agoIVGCVSW-4893 Refactor ILayerVisitor using unified interface strategy.
Finn Williams [Tue, 9 Feb 2021 15:56:23 +0000 (15:56 +0000)]
IVGCVSW-4893 Refactor ILayerVisitor using unified interface strategy.

Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: Id7bc8255a8e3f9e5aac65d510bec8a559bf37246

3 years agoIVGCVSW-5717 Update JsonPrinterTestImpl to match latest ACL
David Monahan [Thu, 11 Feb 2021 11:45:41 +0000 (11:45 +0000)]
IVGCVSW-5717 Update JsonPrinterTestImpl to match latest ACL

 * Updated JsonPrinterTestImpl to use CpuLogitsDLogSoftmaxKernel_#
 * Update ACL pin to: 8958167c8d609566a40c9e618158ebcbdcd3e3bb

Signed-off-by: David Monahan <david.monahan@arm.com>
Change-Id: Ic48d6cc321d8f4cc15c488244f0d69508fad2d1c

3 years agoMLCE-347 Bug fixes in Reduce: QueueDescriptor.validate and init REDUCE_MIN
Teresa Charlin [Thu, 11 Feb 2021 23:05:40 +0000 (23:05 +0000)]
MLCE-347 Bug fixes in Reduce: QueueDescriptor.validate and init REDUCE_MIN

* Allow input tensors of any rank in ReduceQueueDescriptor::validate
* Fix VTS tests failing for REDUCE_MIN due to initialization

Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Id8fba1662ade4e0a967093fe5a53b275847f2393

3 years agoMLCE-360 'ReduceLayer InferOutputShape Issue'
Sadik Armagan [Thu, 11 Feb 2021 13:57:07 +0000 (13:57 +0000)]
MLCE-360 'ReduceLayer InferOutputShape Issue'

* Updated ParseReduce() function in TfLiteParser to read correct axis data
* Remove unused m_TargetWidth and m_TargetHight from ReduceDescriptor
* Updated the ArmNN Serializer Schema

Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I98b6e00ccba1d8ea8c845cb1ae28840e42339629

3 years agoIVGCVSW-5392 TfLiteDelegate: Implement the Batch/Space operators
Matthew Sloyan [Fri, 5 Feb 2021 17:22:28 +0000 (17:22 +0000)]
IVGCVSW-5392 TfLiteDelegate: Implement the Batch/Space operators

 * Added support for BATCH_TO_SPACE_ND and SPACE_TO_BATCH_ND

Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: Ib29333f3e2bc1a18bcc63533da4369b63c45ab90

3 years agoIVGCVSW-5400 'TfLiteDelegate: FLOOR operator support'
Sadik Armagan [Wed, 10 Feb 2021 16:26:44 +0000 (16:26 +0000)]
IVGCVSW-5400 'TfLiteDelegate: FLOOR operator support'

* Added FLOOR operator support to Arm NN TfLiteDelegate

Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I986ce8c5a825f509e0f8b3d257fd5b60834c322f

3 years agoIVGCVSW-5679 Fix Android NDK OOB build
Matthew Sloyan [Tue, 9 Feb 2021 16:46:14 +0000 (16:46 +0000)]
IVGCVSW-5679 Fix Android NDK OOB build

 * Specific OOB builds will fail if flatc is not available.
 * flatc command is now only run if found.

Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: Iab6e082fe35dc3c3dfb78a29e1630c9edbb80be6

3 years agoUpdate ACL pin to 7e20e29904c98adae5a91c6492fd78da88b7a9bf
Nikhil Raj [Tue, 9 Feb 2021 11:05:16 +0000 (11:05 +0000)]
Update ACL pin to 7e20e29904c98adae5a91c6492fd78da88b7a9bf

Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ica5d673e9f6a192b0cfd28c9ad5a5143aecefba7

3 years agoMLCE-347 'REDUCE_MIN, REDUCE_MAX, REDUCE_SUM Support'
Sadik Armagan [Tue, 9 Feb 2021 10:28:54 +0000 (10:28 +0000)]
MLCE-347 'REDUCE_MIN, REDUCE_MAX, REDUCE_SUM Support'

* Added TfLiteParser support for REDUCE_MIN and REDUCE_MAX operators
* Added ACL workloads support for REDUCE_MIN, REDUCE_MAX, and REDUCE_SUM operators
* Added TfLite Delegate support for REDUCE_MIN, REDUCE_MAX, and REDUCE_SUM operators

Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I8085d59946bfd4ab78a59a61f899031ae53371a8

3 years agoIVGCVSW-4901 Add semantic versioning to Parsers and TfLite Delegate
Matthew Sloyan [Wed, 3 Feb 2021 10:43:04 +0000 (10:43 +0000)]
IVGCVSW-4901 Add semantic versioning to Parsers and TfLite Delegate

 * Added Version.hpp to all Parsers
 * Added Version.hpp to TfLite Delegate
 * Updated CMakeLists to use new versions
 * Added GetVersion method to parsers and TfLite Delegate

Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: If29e1e6d9e615f9095ec1c01ad47acfff40b1dd5

3 years agoIVGCVSW-4873 Implement Pimpl Idiom for IRuntime
Kevin May [Thu, 4 Feb 2021 10:27:41 +0000 (10:27 +0000)]
IVGCVSW-4873 Implement Pimpl Idiom for IRuntime

Signed-off-by: Kevin May <kevin.may@arm.com>
Change-Id: I52448938735b2aa678c47e0f3061c87fa0c693b1

3 years agoUpdate ACL pin to dda6914c6e923187c2ca2c3bfd71677e9c9e5c68
Nikhil Raj [Mon, 8 Feb 2021 10:05:13 +0000 (10:05 +0000)]
Update ACL pin to dda6914c6e923187c2ca2c3bfd71677e9c9e5c68

Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I0e29496698b5e7934c2b1c18740527cd9eb23ecd

3 years agoIVGCVSW-5605 Doxygen: Update parser section
Jan Eilers [Tue, 2 Feb 2021 13:18:09 +0000 (13:18 +0000)]
IVGCVSW-5605 Doxygen: Update parser section

 * Removes support.md files from all parsers. Lists of supported
   operators are now kept in doxygen only

Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: I137e03fdd9f41751624bdd0dd25e2db5ef4ef94f

3 years agoIVGCVSW-5605 Doxygen: Add remaining guides to doxygen
Jan Eilers [Mon, 8 Feb 2021 09:23:21 +0000 (09:23 +0000)]
IVGCVSW-5605 Doxygen: Add remaining guides to doxygen

 * Integrates the debian package installation guide
 * Integrates the AndroidNDK guide
 * Integrates the cross compile guide

Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: I2243b15ee3f8e976789494199f12f3cc0fd5f00d

3 years agoArmnnConfig.cmake install to correct directory
Keith Mok [Fri, 8 Jan 2021 23:25:14 +0000 (15:25 -0800)]
ArmnnConfig.cmake install to correct directory

Signed-off-by: Keith Mok <ek9852@gmail.com>
Change-Id: I9b1037275379bdbf452589357576cfa763b7c128

3 years agoIVGCVSW-4143 Add semantic versioning to Arm NN
Nikhil Raj [Wed, 3 Feb 2021 10:27:22 +0000 (10:27 +0000)]
IVGCVSW-4143 Add semantic versioning to Arm NN

Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ibe1200c6d7be9e04821b4a829c83833d44542ad5

3 years agoUpdate ACL pin to cf87f509fc23d02c56569f794a3fb59e1b8be277
Nikhil Raj [Fri, 5 Feb 2021 12:28:54 +0000 (12:28 +0000)]
Update ACL pin to cf87f509fc23d02c56569f794a3fb59e1b8be277

Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I20b69cc042ae5828584b2ecfd2f9694021d7693c

3 years agoMLCE-326 'Support Dilation in Conv2D in ONNX and Tensorflow Parsers'
Sadik Armagan [Mon, 11 Jan 2021 15:15:01 +0000 (15:15 +0000)]
MLCE-326 'Support Dilation in Conv2D in ONNX and Tensorflow Parsers'

Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I4a0f07b1e8f80aff0d29405def1f33bde7944e31

3 years agoRemove LFS configuration
Narumol Prangnawarat [Thu, 4 Feb 2021 11:05:52 +0000 (11:05 +0000)]
Remove LFS configuration

 * Remove LFS configuration
 * Add mock test models for external delegate

Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I9f5b427a995aff22391548cd45821cb2afc8a474

3 years agoIVGCVSW-5592 Implement Pimpl Idiom for Caffe and Onnx Parsers
Kevin May [Fri, 29 Jan 2021 14:24:57 +0000 (14:24 +0000)]
IVGCVSW-5592 Implement Pimpl Idiom for Caffe and Onnx Parsers

Signed-off-by: Kevin May <kevin.may@arm.com>
Change-Id: I760dc4f33c0f87113cda2fa924da70f2e8c19025

3 years agoIVGCVSW-5592 Implement Pimpl Idiom for Tf and TfLite Parsers
Kevin May [Wed, 3 Feb 2021 17:38:41 +0000 (17:38 +0000)]
IVGCVSW-5592 Implement Pimpl Idiom for Tf and TfLite Parsers

Signed-off-by: Kevin May <kevin.may@arm.com>
Change-Id: I4a82aca4a2c47b3c598b91bc0075c09397be728a

3 years agoUpdate ACL pin to 0841ca085301e8ddbc9
Teresa Charlin [Thu, 4 Feb 2021 09:26:07 +0000 (09:26 +0000)]
Update ACL pin to 0841ca085301e8ddbc9

Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I8b27541ec11ee907b80f6e2b4ff9ce3d76320076

3 years agoFix LFS issue
Narumol Prangnawarat [Wed, 3 Feb 2021 13:32:25 +0000 (13:32 +0000)]
Fix LFS issue

Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I6b3321cf0d51c06b742432995ea486c987806afc

3 years agobackends/reference: Add ReduceSum operation support
Sadik Armagan [Wed, 3 Feb 2021 09:29:30 +0000 (09:29 +0000)]
backends/reference: Add ReduceSum operation support

This patch addes ReduceSum operation support for reference backend,
which computes the sum of elements across dimensions of a tensor.

Changelog v1:
- Fix file header descriptions.

Chagelog v2:
- Fix line limit issue.
- Fix type conversion issue.

Changelog v3:
- Remove tabs.
- Modify newly added file headers.

Changelog v4:
- Symbol on header isn't allowed so drop it from newly added file headers.

Changelog v5:
- Remove tabs, fix the use of brackets and align lines correctly.

Changelog v6:
- Add serializer and deserializer support.

Changelog v7:
- Fix build error add missed code.

Changelog v8:
- Rename ReduceSumDecriptor to ReduceDescriptor
    - Update m_KeepDims field data type to bool on ReduceDescriptor
    - Add ReduceOperation field to ReduceDescriptor

- Rename ReduceSumLayer to ReduceLayer
    - Update ReduceLayer to use ReduceDescriptor
    - Update ReduceLayer::ValidateTensorShapesFromInputs() function

- Rename RefReduceSumWokload to RefReduceWorkload
    - Update workload to use ReduceDescriptor
    - Update workload to use Decoders and Encoders

- Remove ReduceSum.hpp and ReduceSum.cpp
- Added Reduce.hpp and Reduce.cpp
     - Move Mean.cpp (which is implementing REDUCE_MEAN) functionality to Reduce.cpp
     - Update RefMeanWorkload to call Reduce function with ReduceOperation::Mean argument

- Remove Mean.hpp and Mean.cpp
- Update the Serializer/Deserializer ArmnnSchema.fbs for ReduceLayer, ReduceDescriptor, and ReduceOperation
- Update Serializer and Deserializer for serializing/parsing ReduceLayer
- Added TfLiter parser Sum test for REDUCE_SUM operator
- Make corresponding changes on front-end and Ref backend to support REDUCE_SUM operator

Changelog v9:
- Fixed build errors.

Change-Id: I8c8e034f3df73f9565b3c18eff51ecca6c542195
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
3 years agoIVGCVSW-5605 Doxygen: Add contribution guide sections
Jan Eilers [Sun, 31 Jan 2021 19:56:23 +0000 (19:56 +0000)]
IVGCVSW-5605 Doxygen: Add contribution guide sections

 * Adds a page for contribution guidelines (Uses md guide)
 * Adds a section for contribution guides (Uses md guide)
 * Minor beautification

Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: Iafd7e3abf9da660ec21a215afada61a27ce928fc

3 years agoIVGCVSW-5605 Doxygen: Add the TfLite Delegate to Doxygen docu
Jan Eilers [Fri, 29 Jan 2021 14:18:13 +0000 (14:18 +0000)]
IVGCVSW-5605 Doxygen: Add the TfLite Delegate to Doxygen docu

 * Moves TensorFlowLiteDelegateSupport.md to doxygen
 * Renames a few .dox files to represent the structure of the documentation
 * Adds sections for build and use guides
 * Integrates markdown guides for the delegate into doxygen

Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: I68b7a29239be88c0617da9bdfce5323ebf26f5bc

3 years agoIVGCVSW-5619 Enable OptimizerOptions for the python external delegate
Narumol Prangnawarat [Fri, 29 Jan 2021 15:38:54 +0000 (15:38 +0000)]
IVGCVSW-5619 Enable OptimizerOptions for the python external delegate

 * Add reduce-fp32-to-fp16, reduce-fp32-to-bf16, debug-data, memory-import
options to external delegate
 * Simplify DelegateOptions
 * Add test mock models
 * Unit tests
 * Configure lfs to manage tflite files

Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I1e4db468862ba03d4cb031347bc307cf940b3cb1

3 years agoUpdate ACL pin to ea857273d8b4a94fb7f1e63ce9068a60259fb9d3
Nikhil Raj [Tue, 2 Feb 2021 10:07:29 +0000 (10:07 +0000)]
Update ACL pin to ea857273d8b4a94fb7f1e63ce9068a60259fb9d3

Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Id43ff3eb59f8c93cfe9fc4bcd76b8496512e2859

3 years agoIVGCVSW-5605 Doxygen: Add PyArmNN to Doxygen docu
Jan Eilers [Fri, 29 Jan 2021 09:50:36 +0000 (09:50 +0000)]
IVGCVSW-5605 Doxygen: Add PyArmNN to Doxygen docu

Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: I43082950c55375f62ecd30236d1c475e4ca89faf

3 years agoIVGCVSW-5605 Doxygen: Move "OtherTools" to "Software Tools"
Jan Eilers [Thu, 28 Jan 2021 16:00:00 +0000 (16:00 +0000)]
IVGCVSW-5605 Doxygen: Move "OtherTools" to "Software Tools"

 * Uses README.md files to reduce duplications

Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: I2cfcb6cf02ac712656cb8c782c70d002df642b97

3 years agoIVGCVSW-5605 Doxygen: Move Converter and Quantizer to Software Tools
Jan Eilers [Thu, 28 Jan 2021 15:38:09 +0000 (15:38 +0000)]
IVGCVSW-5605 Doxygen: Move Converter and Quantizer to Software Tools

 * Using README.md files directly to reduce duplications

Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: I6bd6f6326e608939ac244cc32b329e32bb4802f7

3 years agoIVGCVSW-5605 Doxygen: Move Serializer and Deserializer to Software Tools
Jan Eilers [Thu, 28 Jan 2021 14:45:09 +0000 (14:45 +0000)]
IVGCVSW-5605 Doxygen: Move Serializer and Deserializer to Software Tools

 * Not using the README.md files directly because it doesn't seem to
   be possible to get the content of readme.md combined with the content
   of the support.md files in one page

Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: I1e5073761f3af8a8d498385f3f7586334e7b29ec

3 years agoIVGCVSW-5605 Doxygen: Integrate parsers into Software Tools section
Jan Eilers [Thu, 28 Jan 2021 09:13:24 +0000 (09:13 +0000)]
IVGCVSW-5605 Doxygen: Integrate parsers into Software Tools section

 * Creates new section in doxygen called "Software Tools"
 * Moves the Parser page into Software Tools

Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: I19643074226d7c2e73e560e3abb52f519af1a7b2

3 years agoIVGCVSW-5605 Doxygen: Use readme.md as mainpage in doxygen
Jan Eilers [Wed, 27 Jan 2021 20:04:41 +0000 (20:04 +0000)]
IVGCVSW-5605 Doxygen: Use readme.md as mainpage in doxygen

 * Gives the readme file an update
 * Removes introduction.dox
 * Adds FAQ to doxygen

Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: Ibb67e7f2cac7e55556295eb7851c616561b17042

3 years agoIVGCVSW-5593 Implement Pimpl Idiom for serialization classes
Finn Williams [Tue, 26 Jan 2021 22:30:06 +0000 (22:30 +0000)]
IVGCVSW-5593 Implement Pimpl Idiom for serialization classes

Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I01c7bd314219e58f71505dcb787d606dbded914a

3 years agoIVGCVSW-5374 Provide Android Build for Delegate
Keith Davis [Sun, 31 Jan 2021 18:36:58 +0000 (18:36 +0000)]
IVGCVSW-5374 Provide Android Build for Delegate

Signed-off-by: Keith Davis <keith.davis@arm.com>
Change-Id: Ie8c03153f82434d73572278eedb8a4b5b89ed837

3 years agoIVGCVSW-5484 Add Network loading time to InferenceModel
Matthew Sloyan [Mon, 18 Jan 2021 16:10:20 +0000 (16:10 +0000)]
IVGCVSW-5484 Add Network loading time to InferenceModel

 * Added output log to capture time taken to load network into runtime.
 * This time is cut down when loading a cached network.

Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: I043c177f17d01df35fbe0752ec5d77e350749164

3 years agoIVGCVSW-4874 Provide LayerSupportHandle to frontend users
Francis Murtagh [Thu, 28 Jan 2021 14:25:15 +0000 (14:25 +0000)]
IVGCVSW-4874 Provide LayerSupportHandle to frontend users

 * Add test for new IsBackendRegistered member function of Handle
 * Move deprecated messages to new frontend API of LayerSupportHandle
 * Update delegate to use dot operator for IsXXXLayerSupported

Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: I70d7166e207a10e4b3583a827ca0dda2169bcba1
!android-nn-driver:4940

3 years agoIVGCVSW-5374 Provide Android Build for Delegate
Keith Davis [Wed, 27 Jan 2021 13:12:03 +0000 (13:12 +0000)]
IVGCVSW-5374 Provide Android Build for Delegate

 * Remove double brackets for scalars
 * Add in extra location  in cmake for tf lite dynamic library

Signed-off-by: Keith Davis <keith.davis@arm.com>
Change-Id: I31ef9a955d4677faabedc0068ae2cfbfe570b58c

3 years agoUpdate ACL pin to 4cfab1886549d7582e3867c51278132e5d37681b
Nikhil Raj [Thu, 28 Jan 2021 10:14:35 +0000 (10:14 +0000)]
Update ACL pin to 4cfab1886549d7582e3867c51278132e5d37681b

Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ica17c75dfab52d9b8fada56658b95794d4e58536

3 years agoRemove incorrect use of std::vector.reserve
Jim Flynn [Thu, 28 Jan 2021 07:01:35 +0000 (07:01 +0000)]
Remove incorrect use of std::vector.reserve

Change-Id: Ic45d4c837eaad8b9f19288d4f3b6e8caa3eaf319
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
3 years agoIVGCVSW-5391 'ArmNN TfLiteDelegate: Implement the Space/Depth operators'
Sadik Armagan [Wed, 20 Jan 2021 17:48:07 +0000 (17:48 +0000)]
IVGCVSW-5391 'ArmNN TfLiteDelegate: Implement the Space/Depth operators'

* Added DEPTH_TO_SPACE and SPACE_TO_DEPTH operators support

Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I2595f759181bd7339127e7b114b850b534210dd5

3 years agoIVGCVSW-5390 'TfLiteDelegate: Implement the Normalisation operators'
Sadik Armagan [Fri, 22 Jan 2021 10:53:38 +0000 (10:53 +0000)]
IVGCVSW-5390 'TfLiteDelegate: Implement the Normalisation operators'

* Added L2_NORMALIZATION and LOCAL_RESPONSE_NORMALIZATION opertor support

Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: Ic9e66879cf6469fa8761fb1c9dd5950771f629b0

3 years agoIVGCVSW-5619 Add OptimizerOptions and NetworkProperties to ArmNN Delegate
Narumol Prangnawarat [Wed, 20 Jan 2021 15:58:29 +0000 (15:58 +0000)]
IVGCVSW-5619 Add OptimizerOptions and NetworkProperties to ArmNN Delegate

 * Add OptimizerOptions, NetworkProperties, DebugCallbackFunction
to DelegateOptions
 * Enable OptimizerOptions when the network is being optimized
 * Enable NetworkProperties when loading network
 * Enable DebugCallbackFunction
 * Add error message when loading network
 * Log warning instead of error when operator is not supported but
could fallback to another backend
 * Improve uint16_t CompareData
 * Unit tests

Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I353035afb442774bfeb1c62570a90755c2ceaf38

3 years agoUpdate ACL pin to 6a4ebe1305b544aec1ba0bfc67ed65d94fcc8c2e
Nikhil Raj [Fri, 22 Jan 2021 10:02:38 +0000 (10:02 +0000)]
Update ACL pin to 6a4ebe1305b544aec1ba0bfc67ed65d94fcc8c2e

* Pass in new window parameter to the schedule_op function

Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I8579d2d6e55ab9888471bd780628df0f73438498

3 years agoIVGCVSW-5525 Handle Neon optionality on 32 bit linux platforms
Francis Murtagh [Mon, 25 Jan 2021 10:18:10 +0000 (10:18 +0000)]
IVGCVSW-5525 Handle Neon optionality on 32 bit linux platforms

 * Add neon detection for linux using HWCAPs
 * Add test to check for backend throwing BackendUnavailable exception

Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: Ib74aeb06abe5f88f21ecdd1edb2a1cd20ee2019d

3 years agoMLCE-335 'DEPTH_TO_SPACE and GATHER operator support in TfLiteParser'
Sadik Armagan [Fri, 22 Jan 2021 14:25:31 +0000 (14:25 +0000)]
MLCE-335 'DEPTH_TO_SPACE and GATHER operator support in TfLiteParser'

* Added GATHER operator support to TfLiteParser
* Added DEPTH_TO_SPACE operator support to TfLiteParser

Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: Id5d3b54e2d850eb9f19417029efbeb73a3029e69

3 years agoIVGCVSW-5571 Expose the TfLite Delegate to the TfLite python API
Jan Eilers [Tue, 15 Dec 2020 10:42:38 +0000 (10:42 +0000)]
IVGCVSW-5571 Expose the TfLite Delegate to the TfLite python API

 * Implemented external delegate adaptor interface for TfLite
 * Activated armnn logging for delegate
 * Added logging info to indicate if gpu tuning is turned on
 * Added pytests to ensure functionality of the external delegate adaptor
 * Included the delegate directory into doxygen
 * Added documentation on how to use the external delegate in python

Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: Id3b4588fb0b9ac7e3f47ba2c19feead7beb58e18

3 years agoIVGCVSW-5616 Don't fuse activation if quantization parameters are different
Teresa Charlin [Mon, 18 Jan 2021 18:07:57 +0000 (18:07 +0000)]
IVGCVSW-5616 Don't fuse activation if quantization parameters are different

Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I6504e922113aa9e397f53e570ebcf47e1f133945

3 years agoMLCE-336 'TfLite parser and ExecuteNetwork issues'
Sadik Armagan [Wed, 20 Jan 2021 12:17:00 +0000 (12:17 +0000)]
MLCE-336 'TfLite parser and ExecuteNetwork issues'

* Report the error thrown

Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: If5e5160f43c11a284b919d76b04d9c4d53e9c56c

3 years agoIVGCVSW-5399 'TfLiteDelegate: Implement the ArgMinMax operators'
Sadik Armagan [Tue, 19 Jan 2021 17:24:21 +0000 (17:24 +0000)]
IVGCVSW-5399 'TfLiteDelegate: Implement the ArgMinMax operators'

* Added ARG_MIN and ARG_MAX support to armnn_delegate

Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: Ia000c4b64378e28320164edd4df2902ca13dcda6