Age | Commit message (Collapse) | Author |
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I10bae415c175f4f35f32829fc48473c2ca5fa1d8
|
|
* Added Fused Activation Optimization to both CL and Neon backends.
* Added Fused Activation support to all the CL and Neon workloads
that support it.
* Changed ProfilingTest network to be a Convolution layer
followed by an Abs layer rather than an Activation layer.
* Added IBackendInternal::OptimizeSubgraphView function that can accept a
ModelOptions.
* Network will now call OptimizeSubgraphView passing in the ModelOptions.
Signed-off-by: Keith Davis <keith.davis@arm.com>
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Ib536ac3cbafc7d9b35c139ad9a65b7735262cd9d
|
|
* Add frontend and reference implementation for logical
ops NOT, AND, OR.
* Unary NOT uses existing ElementwiseUnary layer and
ElementwiseUnary descriptor.
* Binary AND/OR uses new layer LogicalBinary and new
LogicalBinary descriptor.
* Add serialization/deserializion support and add missing
ElementwiseUnary deserializer code.
* Add additional Boolean decoder in BaseIterator.hpp.
Signed-off-by: James Conroy <james.conroy@arm.com>
Change-Id: Id343b01174053a166de1b98b6175e04a5065f720
|
|
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I28aace7092cff5743353df1b1de8e7a4691554d3
|
|
* Added Unit Tests to capture all combinations.
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: I04db920a5f5f485dc00b2f16582cf7e0bbef3ef2
|
|
* Fix compiler implicit copy deprecation warning.
* Simplify copy operator by removing unnecessary equality comparison.
Now just does pointer comparison instead.
Change-Id: I9ebe170c637c636919b9d8729a78449148b7f83e
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
This patch adds int32 and int64 ArgMax op support.
Current ARMNN already has ArgMax op but not used, and
it doesn't support int64 output type.
So this patch adds a new type, Signed64, and also adds
ArgMinMax computation function for int64 type support.
In default, output tensor type of ArgMax op is int64 in case of
tensorflow lite model so this patch makes a proper function - ArgMax op
for int64 or int32 - to be called according to parsed output_type value.
With this patch, ARMNN supports both types - int64 and int32 - for
ArgMinMax op.
Changelog v1:
- Check if output data type of ArgMinMax op is valid or not.
- Use template function to support int32 and int64 types of ArgMinMax function.
- Keep using Signed32 as default data type of m_Output_Type.
Change-Id: I7a8e7e38dd9e5acc81464571d8b4d51378fc7f14
Signed-off-by: Inki Dae <inki.dae@samsung.com>
|
|
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I4eb3e27837aea926593d49f9ccea07bab8388d5b
|
|
factory'
* Pass ModelOptions to WorkloadFactory
* Updated signature of CL and NEON Convolution2d workloads added FastMathEnabled param.
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I536178be8e4dd4083489e69febadaf0feeba46d2
|
|
* Add unit tests to check if Quantization info copied correctly
Signed-off-by: Kevin May <kevin.may@arm.com>
Change-Id: I7bb7bde5d97e82c57252c6d5131fbe21ad3096d2
|
|
* Introduced ModelOptions to IBackendInternal
* Introduced ModelOptions to Network
* Added FastMathEnabled parameter to Conv2d Validate function in CL and NEON
* Added Optimizer tests
Signed-off-by: Ryan OShea <Ryan.OShea2@arm.com>
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: Ib54c1e82cb3d89a52756ed499cf91b6a7fdb2063
|
|
* Added functionality to query if TensorHandleFactory supports InPlaceComputation
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: Icf5bfc5f999fc5d03681dcb8cec88d921842458b
|
|
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: Ic7c288fd829d7f1f1ae2910c47fbccdd635def8f
|
|
* Default importEnabled to false
* Improve error messages
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I17f78986aa1d23e48b0844297a52029b1a9bbe3e
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ida6100eb62c46971b6958addfc69f15eb0634ba2
|
|
Change-Id: I180f84c493a9b2be4b93b25d312ebdd9e71b1735
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
|
|
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I0a2babe5b5b09eb81c9900dc3a05071034a0440b
|
|
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: Ie8acb9c729af4f95488aecf795f45ff12364f9ca
|
|
* gcc-arm-linux-gnueabihf/xenial,now 4:5.3.1-1ubuntu1 amd64 complains
about error: array must be initialized with a brace-enclosed initializer
in include/armnn/Tensor.hpp:122:81.
Signed-off-by: Colm Donelan <Colm.Donelan@arm.com>
Change-Id: Ib8f72bbcf86586a704a0e98c5ba07fefdf5665a8
|
|
Change-Id: Id69519fd9ef57716de4e389ed4156710a904c701
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
|
|
* Add Rank front end
* Add Rank reference implementation
* Add Rank serialization support
* Add Scalar serialization support
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I06e4a468c2a84e79bae2e6c5348596bbbf853b4b
|
|
* Add m_OutputShape and m_OutputShapeEnabled to
TransposeConvolution2dDescriptor.
* Update TfLite parser to populate m_OutputShape if found in the model.
Handle both Signed32 from tflite files and QAsymmU8 from test fixtures.
* Update TransposeConvolution2dLayer to use m_OutputShape instead of
InferOutputShapes if specified.
Signed-off-by: Colm Donelan <Colm.Donelan@arm.com>
Change-Id: Ia6933065375eb8006c916f1ca67c38dc50bc205c
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I63f97fad080dbfeec6433c2548f0311173051a6a
|
|
!android-nn-driver:3302
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Ifbc49acb5272f8a36719bb68676e44817190537d
|
|
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: Ideaae5280702aae6c73f3b4e4cee9f71a8386fda
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I70ef1a9f3cefa1d4cf9220f0e13131d11e7c6418
|
|
* Added new fill layer
* Added visitor tests
Signed-off-by: Ryan OShea <Ryan.OShea2@arm.com>
Change-Id: Iea677014866b4f2d514004623f59ee83f3c0eef8
Signed-off-by: Keith Davis <keith.davis@arm.com>
|
|
Change-Id: Ia4b4bb3be0ed6e933c77d58f8e9879b1370e9537
Signed-off-by: Laurent Carlier <laurent.carlier@arm.com>
|
|
* Added AlignCorners and HalfPixelCenters to Resize and ResizeBilinear
* Updated Serializer and Serializer tests
!android-nn-driver:3280
Signed-off-by: David Monahan <david.monahan@arm.com>
Change-Id: Ice3bb448c239b04323854641525bfe0808c03b2e
|
|
Change-Id: Ie205d8146f5bb1920bf001b7623ead79e2ab9e48
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
|
|
Change-Id: Ieccb26190d80e570ddef8d7c22e824eda1b92d7f
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
|
|
reduce traffic
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: Ia55c52c12fe3d30eb47bc42c932a33c620dc9197
|
|
* Implemented CLTuning flow for ExecuteNetwork tests
* Added --tuning-path to specify tuning file to use/create
* Added --tuning-level to specify tuning level to use as well as enable extra tuning run to generate the tuning file
* Fixed issue where TuningLevel was being parsed incorrectly
* Added measurements for initialization, network parsing, network optimization, tuning, and shutdown
* Added flag to control number of iterations inference is run for
Signed-off-by: alered01 <Alex.Redshaw@arm.com>
Change-Id: Ic739ff26e136e32aff9f0995217c1c3207008ca4
|
|
* Bump major version to 21
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: I35237dfa3683d962871bad6b0353f6910d7c3e3b
|
|
UNREGISTERED_BACKENDS
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I3600dd15f97ccd4ab745deb87d06ba978e2a0b11
|
|
Change-Id: Ib49a8cbbf323da4109cdab9750e6c4d276e484b7
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
|
|
* Fix for StringTokenizer utility method to match Boost::Split implementation
Signed-off-by: David Monahan <david.monahan@arm.com>
Change-Id: I50e047ff72191da9aa06b71370c4354c5a78eb9b
|
|
* Adding HalfPixelCenters parameter to Resize Descriptor
!android-nn-driver:3061
Signed-off-by: David Monahan <david.monahan@arm.com>
Change-Id: I2713125525f434f5abe5a87183723e482df27a43
|
|
* Removed split, classification, trim, string, join, contains
* Added StringUtils.hpp to replace the removed Boost String functionality
Signed-off-by: David Monahan <david.monahan@arm.com>
Change-Id: I8aa938dc3942cb65c512cccb2c069da66aa24668
|
|
* as replacement for boost::polymorphic_pointer_downcast
* added PolymorphicPointerDowncast
* added related unit test
* added description to PolymorphicDowncast
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: I47e94344c1c21941865549a5632cfb7cad804d35
|
|
* exchange boost::polymorphic_downcast with armnn::PolymorphicDowncast
* remove unnecessary includes of boost::polymorphic_downcast
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: Ie603fb82860fe05fee547dc78073230cc62b2e1f
|
|
* Change boost assert to armnn assert
* Change include file to armnn assert
* Fix ARMNN_ASSERT_MSG issue with multiple conditions
* Change BOOST_ASSERT to BOOST_TEST where appropriate
* Remove unused include statements
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I5d0fa3a37b7c1c921216de68f0073aa34702c9ff
|
|
* Add Activate/Deactivate command handlers
* Add IReportStructure, INotifyBackends single function interfaces
* Add overrided mechanism to report structure in Runtime.cpp
* Add overrided mechanism to notify backends in ProfilingService.cpp
* Add optional IReportStructure argument to ProfilingService constructor
for use in ActivateTimelineReportingCommandHandler
* Refactoring and tidying up indentation
* Removal of unused code in ProfilingUtils.cpp and ProfilingService.cpp
* Added GatordMock end to end test
* Fixed an issue with SendCounterPacket sending duplicate packets
* Fixed an issue with DirectoryCaptureCommandHandler handling of Optional
Signed-off-by: Keith Davis <keith.davis@arm.com>
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I5ef1b74171459bfc649861dedf99921d22c9e63f
|
|
* Use default keyword for armnn::Optional assignment.
* Use default keyword for BFloat16 copy constructor and assignment.
* Remove unnecessary const from static_cast template argument which
was giving ignored-qualifiers warning.
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: Ie3f4ce0a0c199a578d8cca2fea8f5dcef63dba4d
|
|
* Add ReduceFp32ToBf16 to OptimizerOptions
* Add ConvertFp32NetworkToBf16
* Add utility functions to insert conversion layers
* Add constant conversion BF16 <-> FP32
* Unit tests
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: Iaff77e20c721400b052cb37eb9ef6fe16d7abaff
|
|
* Added new layer QLstm (Android R HAL 1.3)
* Made necessary updates to APIs
* Added unit tests
* This layer is functionally equivalent to the
original unquantized LSTM layer with some
additonal quantization features added. Due
to this, original LstmParams are used for
this layer.
Signed-off-by: James Conroy <james.conroy@arm.com>
Change-Id: I5b7f2d2fb6e17e81573b41a31bc55f49ae79608f
|
|
* Added new m_FileFormat variable in ExternalProfilingOptions
* Added new profiling option to ExecuteNetwork
* Added check for file format in ProfilingConnectionFactory
* Added test in profiling tests
Change-Id: I0e9cb8ecac919dc0ed03dcf77324a65621f07ae7
Signed-off-by: Isabella Gottardi <isabella.gottardi@arm.com>
|
|
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I9099a4f840fb747336f77d20a0868b64e801a310
|
|
* implemented activation layer end to end test
* adds support for different tolerances in layer tests
* added tests for Elu (Ref, Cl, Neon)
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: I81e28cfb4456e815bae2fb31f5c345134ff2432f
|
|
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I345c39a10a4693a500aa1687d9a5cee76da791c3
|