Age | Commit message (Collapse) | Author |
|
* Generic layer parameters now show up in dot file
* Convolution layer parameters have also been added to dot file
* ExecucteNetwork has an additional -v flag which generated dot file if there
Change-Id: I210bb19b45384eb3639b7e488c7a89049fa6f18d
Signed-off-by: Andre Ghattas <andre.ghattas@arm.com>
Signed-off-by: Szilard Papp <szilard.papp@arm.com>
|
|
* Updates ACL pin to include patch for asymmetric padding in TransposeConvolution2D, used by FSRCNN
!android-nn-driver:1857
Signed-off-by: Matthew Jackson <matthew.jackson@arm.com>
Change-Id: Ie9c8c75b6cff3caa87623ec4021e03d409fdb18a
|
|
Change-Id: I30ae52d38181a91ce642e24919ad788902e42eb4
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
|
|
SendCounterPacket.SendPeriodicCounterSelectionPacket() function
Signed-off-by: Ferran Balaguer <ferran.balaguer@arm.com>
Change-Id: Ib034a4f5ca589759d925e3dd0ca50e5a3dfa74c5
|
|
Signed-off-by: Ferran Balaguer <ferran.balaguer@arm.com>
Change-Id: I0d9b0ab12f17cb86544163ce3f0dc4945151e9e1
|
|
* Added "output-tensor-files,w" option to save output tensors to a file
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: Ida457177c5cbd7dca228772405fd505d03b61bf9
|
|
Change-Id: Id49e43680b306e762672f2681eaf45788dcfcdd0
Signed-off-by: Surabhi Mehta <surabhi.mehta@arm.com>
|
|
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: Icf39434f09fd340ad664cb3b97b8bee6d9da4838
|
|
* If the number of the declared output types does not match
the number of outputs, throw an error (just like we do for
the inputs)
Change-Id: I1cb873bf443a31ecdbc11195462e9614ae3a6637
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
|
|
* Renamed ARMNN_COMPUTE_REF_ENABLED to ARMNN_REF_ENABLED in the
Android makefiles
Change-Id: I12af2ca00c719568274585482d428b035674737c
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
|
|
* Changed the default value of the new ARMNNREF option to ON in
the global makefile, so to always build the reference backend
by default, thus keeping the same behaviour as of the previous
releases
Change-Id: Id4941522ac7987c797ac8331ea421edb2a54287f
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
|
|
Signed-off-by: Matthew Jackson <matthew.jackson@arm.com>
Change-Id: Id7ab186ec607ff6e5ee6869c4ad562af4c40b97a
|
|
ElementwiseTestHelper
* Refactored tests for element-wise operations to use ElementwiseTestHelper
* Moved the etasts for each operation in a separate file under backendsCommon/test/layerTests
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: Icefb6b35df78b9619f69378229789505bf92670e
|
|
* Renamed ARMCOMPUTEREF to ARMNNREF (and relative symbols) as the
previous name was misleading
!android-nn-driver:1819
Change-Id: I912e9f521750b91539e48f8a2fb4de73fb6f7425
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
|
|
* Added null checks prior of using either the source or the destination
handle factory when checking if the tensor requires to be copied
Change-Id: Icc6737562849be5e7d1a62243327366e06312eb9
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
|
|
* FCRN and FSRCNN aren't supported on all backends yet.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: Ibaddfba731224aac24de05c225fb94efd3fe7f94
|
|
* Added ARMCOMPUTEREF option to the build guides, as the
reference backend is not built by default
Change-Id: I2cd8dab12ed72a795ff79fe1087ab8bf7606694e
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
|
|
* Adds compatibility between Cl and Neon
* Adds related unit test
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: Iaa454ea2a6392c89c0a83836c3156d4ddb354879
|
|
Failing VTS tests were "NeuralnetworksHidlTest.depthwise_conv2d_*"
In depthwise convolution there was a difference in weight tensor channel
order between the reference and ACL implementations. This specifically related
to NCHW. This commit:
* Adds ReorderWeightChannelsForAcl to WorkloadUtils which will correct the weight tensor channel order.
* Add unit tests to detect this problem.
Signed-off-by: Colm Donelan <Colm.Donelan@arm.com>
Change-Id: Icaeac08e14b3d5da9e222ad2f118db55ebb15d09
|
|
Signed-off-by: Ferran Balaguer <ferran.balaguer@arm.com>
Change-Id: I6f16ea0dca359283a3b187e2f046f82a7dc2ff7c
|
|
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I912312f31d4fd82b23bafe8e3ec461b179f3e97a
|
|
* Created classes Device, Counter, Category, CounterDirectory
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: Iaec4b0e154d962983c60460714bafcc1fb16f47e
|
|
* Added path override for dynamic backend loading
* Do not default to CpuRef, as there could be dynamic backends loaded at
runtime
* Do not check right away whether the backends are correct, as more of
them can be loaded at runtime as dynamic backends
Change-Id: If23f79aa1480b8dfce57e49b1746c23b6b9e6f82
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
|
|
* Create first version of PacketVersionResolver class
* Add basic unit test
* Move existing classes inside the armnn::profiling namespace
* Add utility methods for Version
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: If0ea0e1b9dea7fbfcd8b808e97b1e2aa91964dfa
|
|
* CMake "install" commands require a RUNTIME argument for platforms with
DLLs (e.g. Windows).
* Replace use of non-standard variable length array with vector
* Remove unnecessary #include of unistd.h
* Add #ifdefs to dynamic backend code to disable for non-Unix platforms
where you can't use dlopen etc. We could implement this properly for Windows
later using LoadLibrary etc., but for now erroring is fine.
* Add missing #include of <algorithm>
Change-Id: Ic8ef5fd599b37bf8772510157b6e479819f6a1eb
|
|
Signed-off-by: Ferran Balaguer <ferran.balaguer@arm.com>
Change-Id: I87d003ae14575d7d7be67b2a7d00d69ef6201849
|
|
* Made the build of the reference backend depend on a new ARMCOMPUTEREF
macro
* Made the relevant targets dependent on the ref backend
* Moved Cl and Neon static registry initializers to separate files
* Wrapped some of the unit tests into proper ifdefs where necessary
Change-Id: I7f2c42699682630233a4c4b6aed2f005083de189
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
|
|
Signed-off-by: Ferran Balaguer <ferran.balaguer@arm.com>
Change-Id: I64f82c0e3c5cddcaebe0d5001020880a759ec444
|
|
* Updated the NDK build guide to include instructions on what
extra files to deploy for running the dynamic backend unit test
Change-Id: I0a77b0bf911cfdd90be62f136dd06c118810d0c8
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
|
|
Signed-off-by: James Conroy <james.conroy@arm.com>
Change-Id: Ibfd5a81b2dbf9eeef49f6209885798804adee5a4
|
|
Signed-off-by: FinnWilliamsArm <Finn.Williams@arm.com>
Change-Id: Ibf2b5ce5e50d72d661a7c720c1f3bb1c0d811700
|
|
* Move DeepSpeaker, FCRN and FSRCNN from TensorFlowSupport.md
to TensorFlowLiteSupport.md
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I82d508d3599073eb8f6638994a91f46b4b95c247
|
|
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I3da43122240fda7864e0932d47b3efeea8bbed40
|
|
* Reordered and edited inputs in ParseTransposeConv method
* Updated test cases to reflect changes
Signed-off-by: Matthew Jackson <matthew.jackson@arm.com>
Change-Id: Icd090cf6ab340eed4f098ef8641daf7c6e0d0949
|
|
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I9d19ae4559a98b9e740c1d4d05add0c5788093d6
|
|
* Fixed Quant8 VTS test failures where an output value should have been greater than 255 before a negative bias was applied.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: Ie0084c1c8c4a4b5f069112d523765ed338277e58
|
|
* NEON support for TransposeConolution2d
* Indentation fix on SpaceToDepth LayerSupport method
Signed-off-by: Keith Davis <keith.davis@arm.com>
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Signed-off-by: Aron Virginas-Tar <aron.virginas-tar@arm.com>
Change-Id: Ie3a01a22e05f62f475f768dfe05ce561d2f3b0ad
|
|
Signed-off-by: Ferran Balaguer <ferran.balaguer@arm.com>
Change-Id: I94bd191f88e0911ad4e4727610e81cd7afa95512
|
|
* Fixed bug in multi-channel test and reference workload implementation
* Enabled multi-channel tests on CL backend
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I08bb523bc68d9c93a1012b4f487a5bce36a085b1
|
|
* Added ParseTransposeConv to TfLite Parser
* New TransposeConv test file
* Updated documentation for supported Transpose Convolution
Change-Id: Id7356d8525556805c164af693ae2b16f6a8492fa
Signed-off-by: Matthew Jackson <matthew.jackson@arm.com>
|
|
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I43a46a9ec4adef35736af8de67916bfda967da0a
|
|
* Adds ClTensorHandleFactory
* Includes some refactoring of NeonTensorHandleFactory
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: I9f0874b1945050267c5ece970e6d9b200ed8a865
|
|
* Now the utility function RegisterDynamicBackends returns a list of
the backend ids that have been registered
* The list of registered ids is added to the list of supported backends
in the Runtime
* Added unit tests
Change-Id: I97bbe1f680920358f5baba5a4666e4983b849cac
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
|
|
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: Idebe0c3f956ccac39ef8bf139d693b76e839af7a
|
|
Change-Id: Id429f7d9176c775953c1261c5a3e9f1d565927c1
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
|
|
Change-Id: I51e34068d79ba660ae2f16b22ad2bb8191d473fa
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
|
|
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I442913dc5e8ac8b53c00feef430a77991e700556
|
|
The following NeuralNetworkTests tests were failing on GpuAcc and CpuAcc:
GeneratedTests.softmax_v1_2_relaxed
GeneratedTests.softmax_v1_2_quant8
GeneratedTests.softmax_v1_2_2
GeneratedTests.softmax_v1_2_relaxed_2
GeneratedTests.softmax_v1_2_quant8_2
The default value for Softmax axis parameter in Android is -1 but is 1 in ACL.
Detect and handle this in ArmComputeUtils.ComputeSoftmaxAclAxis.
Signed-off-by: Colm Donelan <Colm.Donelan@arm.com>
Change-Id: Ibb0660e4cb0dc6bd4c804c4397fbd61f38acdd9c
|
|
* Increased MaxNumOfTensorDimensions and fixed issues related to its use
* Fixed issues caused by assuming 5d tensors are invalid
* Updated ArmComputeTensorUtils for 5d tensors
* Added 5d tensor unit tests for add, mul, stack and reshape (needed by IVGCVSW-3527)
Signed-off-by: Matthew Jackson <matthew.jackson@arm.com>
Change-Id: I5bcd64942d0d04efcc6c5acb240ad4b88e010743
|
|
Change-Id: I59ac9b32ac594161bdc5e1de2cdee02d79fc1992
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
|