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>
|
|
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: Icf39434f09fd340ad664cb3b97b8bee6d9da4838
|
|
* 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>
|
|
* 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>
|
|
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
|
|
* 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
|
|
* 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
|
|
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
|
|
* 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
|
|
* Fixed possible driver crash due to supportedTypes arrays with the wrong size.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I52702b84089d02d3c63ff7aa5923a9f5628bec91
|
|
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I496f95ab464f3a38e0601799a6ff6ba5ffe3a776
|
|
* Change Getter Signatures to follow coding guidelines
Change-Id: Ic02621e834dbf79b9df63f8b4c6339f71651e944
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
|
|
RefLayerSupport::IsTransposeConvolution2dSupported()
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I85a9563e2d12a5eb9dbcac1b70563a303905b67b
|
|
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: Ib9271920b39fb9d730006c79a322e32008096b56
|
|
* Now supports channel multiplier != 1 in Ref TransposeConvolution2d
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: Ice95444025311b8b952c8f7f5fa0f1ecf483df41
|
|
* Fixed Max and Min VTS test failures.
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I133f5ff43774f74ad6e1c698a3570066ad45527c
|
|
an example in the docs
* Wrapped the reference backend into a dynamic backend
* Moved the static registration code to a separate file, so that
it is possible to create the reference dynamic backend that does not
register statically into armnn
* Added unit test
Change-Id: I1074d21b020820f9ac8c7178388be773b447555a
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
|
|
* Rename MemoryStrategy to EdgeStrategy
* Add MemImportLayer
* Import memory rather than copy when possible
Change-Id: I1d3a9414f2cbe517dc2aae9bbd4fdd92712b38ef
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
channel multiplier != 1
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I784bbff3f7b6650881d3f70ba7cd1891171195b1
|
|
* Added Int32Decoder and Int32Encoder to decode INT32 tensors
* Changed MakeDecoder to return ScaledInt32Decoder only
if the scale is different from 0, i.e. for quantized bias
tensors
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I278061d445d1c549c7ace11f51aa172ce7c691ae
|
|
* Fixed FP16 failures on Max, Min, BatchToSpace on Gpu
* Fixed Signed32 skips on Maximum and Minimum
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I4bea19af1a0ae4c8950af8c6d5d68622cdd9b674
|
|
* Added CL backend support for Stack
* Added unit tests for Stack on the CL backend
* Refactored unit tests to support generic data types
Signed-off-by: Matthew Jackson <matthew.jackson@arm.com>
Change-Id: I38ee3e9d8947ea98a3104c982698001e704d7d89
|
|
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: Ib93c94a15fe15495664d509630cce373a69e1612
|
|
* Fix reference L2 Normalization workload to support < 4 dimensional tensors
* Add unit test for L2 Normalization with 2d tensor to Reference, Neon and CL test suites
* Fix typo in StackLayer
Signed-off-by: Matthew Jackson <matthew.jackson@arm.com>
Change-Id: I48a6a1289bcb02955b24f261bc70b467bd1abc23
|
|
* Pad value for QASYMM8 is no longer stored in quantized form.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I048e1d233353c0560ae03a7cc1ed5199295352bc
|
|
* Replace u_int32_t with uint32_t
* Replace size_t with uint32_t for initializer list of TensorInfo
* Replace variable size arrays with std::vector
* Replace reference to local variable during its initialisation
Change-Id: I298b3995f1525f90a1ab2416d7e270315698fae3
|
|
* Add Axis parameter to Softmax Descriptor
* Add new reference implementation for Softmax using Axis parameter
* Add unit tests to cover each Axis
Change-Id: Iafac2275d2212337456f2b1b56b0f76f77fb9543
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
|
|
* Remove multiplier check in TfLite parser
* Add reference unit test for depthwise multipler of 64, as in DeepSpeaker
Signed-off-by: Matthew Jackson <matthew.jackson@arm.com>
Change-Id: I787339ab4c4d269333985353d191202d070906ba
|
|
Change-Id: I041bdf9e721a4384ea3c2be0184787dd1f4ea08e
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
|
|
* Added reference workload for the Stack layer
* Added factory methods
* Added validation support
* Added unit tests
Signed-off-by: Matthew Jackson <matthew.jackson@arm.com>
Change-Id: Ib14b72c15f53a2a2ca152afc357ce2aa405ccc88
|
|
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: Idb1325cba730dbf62b4742e4078220ef97d4b526
|
|
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I7f4c722141837939fd8904c52e75704a15c8a5e3
|
|
strides, dilation and padding
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Iea99a162e1f0c823cd0f8bc0ae2fb5f461778515
|
|
!android-nn-driver:1461
Change-Id: I9d8fe7adf13832ed0cbcfe98b2353c2f37011d22
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
|
|
* Add support of QuantisedSymm16 to Pad
* Fix custom padding tests
* Add unit tests for Pad QuantisedSymm16
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: Ieb9a4492760b13fa030a42eb4d38fd9ffd7a8c76
|
|
* Refactored existing EndToEnd tests, moved
tests in reference to backendsCommon.
* Enabled EndToEnd tests for CL.
* Added new Ref/CL CreateWorkload tests.
Signed-off-by: James Conroy <james.conroy@arm.com>
Change-Id: I0a5e52961a8aca540d43241a3805d19c9c6ff56c
|
|
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: Id6ab073ae3e0ff5f60c2f4bef975798ce71c9f88
|
|
refactor to be done
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I6dbf6a2aa328b8c843632e1231931b4e1c6888bb
|
|
* Added CL backend support for SpaceToDepth.
* Enabled unit tests for SpaceToDepth on CL.
* Renamed unit tests to make them type-agnostic.
* Added QSymm16/S16 support to ClTensorHandle.
Signed-off-by: James Conroy <james.conroy@arm.com>
Change-Id: I417d82946142ed619c447428bf0b0c4a2116c004
|
|
* Renamed m_padValue to m_PadValue to bring it in line with
our naming conventions
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I071aa42c9be495462c64697e5a923a5ec55de146
|
|
Simple pool memory manager for use in the reference backend,
in order to make the backend usable for testing large networks.
Change-Id: I5694da29052c60f95b57da595c64cc114d75b8ba
Signed-off-by: Matthew Bentham <Matthew.Bentham@arm.com>
|
|
* Refactor and add QSymm16 to IsDepthwiseConvolutionSupported
* Refactor and add QSymm16 to IsEqualSupported
* Refactor and add QSymm16 to IsGreaterSupported
* Refactor and add QSymm16 to IsSplitterSupported
* Refactor and add QSymm16 to IsStridedSliceSupported
* Refactor and add QSymm16 to IsMemCopySupported
* Refactor IsFakeQuantizationSupported
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I4f115a5535748fc22df8bc90b24b537fd5dd95b8
|
|
Change-Id: I7a812eafc8c73d074049ba95189cbc17d276eee3
Signed-off-by: Matthew Bentham <matthew.bentham@arm.com>
|
|
consider 4 neighbors instead of 2.
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Ia724b35f723157e9f51b5345964200f126b98267
|
|
!android-nn-driver:1451
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: Ieedbce1f6e95891137a250fdd07e2f7e4e1f4828
|