aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2021-02-23Updating Readme and Integrator guidev21.02branches/android-nn-driver_21_02Nikhil Raj
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: Icd649285e44c427ec6c973cc313339276e6fb8c8
2021-02-16IVGCVSW-5686 Add GpuAcc MLGO tuning file configuration argument to nnapiFinn Williams
Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: I15ca7db703065b0c70766a18b1a9a213834f39e0
2021-02-16IVGCVSW-4873 Implement Pimpl Idiom for INetwork and IOptimizedNetworkFrancis Murtagh
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com> Change-Id: I32dc7654b13384e95684073c2fc51cd147085367 !armnn:5012 Change-Id: I32dc7654b13384e95684073c2fc51cd147085367
2021-02-15IVGCVSW-5665 Basic NN Driver support for next OS VersionSadik Armagan
Signed-off-by: Kevin May <kevin.may@arm.com> Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I1e1db52322092c6b1b7ac6183c3adc90aabcec24
2021-02-12IVGCVSW-5685 Add CpuAcc specific configuration option numberOfThreadsMatthew Sloyan
* Added --number-of-threads command line option to android-nn-driver !armnn:5068 Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: I248326bf3c0355a7a17b70cb1aac7b7976820c12
2021-01-28IVGCVSW-5487 Update setup and Android.bp files to build v8.2a driverNikhil Raj
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: I6c068d50f4d6ccc063b64806d47dd72a81514701
2021-01-28IVGCVSW-4874 Provide LayerSupportHandle to frontend usersFrancis Murtagh
* Update to use dot operator for IsXXXLayerSupported() * Call LayerSupportHandle member funciton to check is Backend Registered Signed-off-by: Francis Murtagh <francis.murtagh@arm.com> Change-Id: If0b9876068db8957a8bdb690ad323cd8dce544a4 !armnn:4924
2021-01-13IVGCVSW-4417 'Serialise ArmNN Model on android-nn-driver'Sadik Armagan
* Implemented serialization of the network on android-nn-driver !armnn:4850 Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I3caf07bd4d1d2a3068c58f0b344303c4cf977ca6
2021-01-11IVGCVSW-5485 'Add CacheLoadedNetwork options to Android NN Driver'Sadik Armagan
* Added Flatbuffers dependency to android-nn-driver * Added CacheLoadedNetwork options to android-nn-driver Options will be android.hardware.neuralnetworks@1.3-service-armnn -v -c GpuAcc -n arm-armnn -s -q <file_path> & Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I2cdf0b84062cb1c6ad4346cd64b00161cfe85920
2020-11-25IVGCVSW-5347 Update Android-NN driver FAQ.md and IntegratorsGuide.md.Sadik Armagan
FAQ.md: * Reducing the priority of Boost in one FAQ entry. * Changing the tense of another entry referring to the upcoming Android 10 release. IntegratorsGuide.md * Added reference to Android R in prerequisites section. * Added references to Android R in several sections. * Removed references to "pre-release" Android R. Signed-off-by: Colm Donelan <Colm.Donelan@arm.com> Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: If2a07908dc8d2157532859e25afdd70fe7827c93
2020-11-20IVGCVSW-5347 Update Readme for 20.11Teresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: If094e618480c874222e6934d7829d2e8050005d8
2020-11-17ConvertMaximum. Fix wrong function name in logTeresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I909da6857e5f5fa3aa0be62e926d23c67389df7d
2020-11-16Added SECURITY.md fileMike Kelly
* New file contains the security policy, vulnerability reporting procedure and a PGP key that can be used to create secure vulnerability reports. Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: I60dac5b0340197855916823b268584245c207893
2020-11-12IVGCVSW-5090 Add android-nn-driver Support for Logical operatorsNarumol Prangnawarat
* Add ConvertLogicalBinary * Add support for LOGICAL_AND, LOGICAL_NOT, LOGICAL_OR Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: I4dcecbebe031915b8c237fd5b9b92c8844847fb7
2020-10-30IVGCVSW-5267 Remove use of boost::array from unit tests.Colm Donelan
* Boost::array is used in a small number of nn driver unittests. It can be directly replaced by std::array in C++ 11. Signed-off-by: Colm Donelan <Colm.Donelan@arm.com> Change-Id: I4c6f4489b7cab8e60c6b76172c3027f953d63e3c
2020-10-30IVGCVSW-5267 Remove boost from core android-nn-driverJames Ward
Signed-off-by: James Ward <james.ward@arm.com> Change-Id: I156d0951eea3958a245b729321647585a19c65e2
2020-10-29IVGCVSW-5267 Remove boost from core android-nn-driverJames Ward
* WIP !armnn:4231 !armnn:4287 Signed-off-by: James Ward <james.ward@arm.com> Change-Id: I7844efc84fac018d8aad1f72dd236ede3fd8e7f2
2020-10-23IVGCVSW-5353 - Fix skipped concat VTS testsDavid Monahan
* Added 3D permutation vector to prevent mismatch between mappings and numDimensions in dynamic concats Signed-off-by: David Monahan <david.monahan@arm.com> Change-Id: Ia580deaa8a4f6245c7e4d319d5d0ed837c7dc02a
2020-10-21IVGCVSW-5445 Fix for Android-NN-Driver cmd line parametersMike Kelly
* If the Android-NN-Driver encounters unexpected or unknown parameters it will exit after displaying the application help text. Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: I47c66ccc4768b6cd5ffc4cc79de0e9b61bcc18c2
2020-10-13IVGCVSW-5335 Documentation for fast_mathMike Kelly
* Changed documentation for fast_math to add warning about possibly reduction in precision. * Added -h,--help option to display command line help for the driver. * Added -V,--version option to display ArmNN version information for the driver. * Changed driver to display an error and the command line help if it cannot start for any reason. * Backend no longer defaults to GpuAcc. Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: I270b10ec9d485fd25e25680fc29ea1fc2b0e8e1d
2020-10-09IVGCVSW-5359 Fix Transpose Conv2d Dynamic testsFinn Williams
Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: I377af50c1ae17aef9b730d1c8ef6a2b54d9d4c5c
2020-10-09IVGCVSW-5357 Fix skipping Dynamic Grouped Conv2d testsFinn Williams
Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: If1be1fcd289e83661a0ad03574a36cbbd9266c88
2020-10-08IVGCVSW-5278 Fixing an error in the definition of fp16-enabled parameter.Colm Donelan
* Swap the order of short and long parameter definition for fp16-enabled. Signed-off-by: Colm Donelan <Colm.Donelan@arm.com> Change-Id: If36af5b840739a97baaa9fc56476a05815792862
2020-10-07IVGCVSW-5278 Switch Android-nn-driver/DriverOptions.cpp over to cxxoptsColm Donelan
* Add armnn/third-party to LOCAL_C_INCLUDES in Android.mk. * Update DriverOptions.cpp to use cxxopts instead of Boost:program_options Signed-off-by: Colm Donelan <Colm.Donelan@arm.com> Change-Id: I54c080e3b01f128c05d73ed5b7b76e5e64bd63ac
2020-10-07IVGCVSW-5298 Remove boost::format from Android-nn-driverColm Donelan
* Replaced with stringstream, string or filesystem::path Signed-off-by: Colm Donelan <Colm.Donelan@arm.com> Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: I2aa80d88cc0eaff5de4dc6a121370ebf41dcb0a8
2020-10-02IVGCVSW-5356 Fix skipping VTS DynamicOutputShape FullyConnectedFinn Williams
Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: I011466158b6736670bafba474e8c9ce12c38e229
2020-10-01IVGCVSW-4566 Add support for EXP operatorTeresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: Ia3909f32a837ade88e848de7f9ee0bf003bc8c01
2020-09-30MLCE-233 Added ability to enable fast_math through the NNAPI driverMike Kelly
* Added -a command line option to enable fast_math on Neon/CL when launching the NNAPI driver * The invocation will look something like: /vendor/bin/hw/android.hardware.neuralnetworks@1.3-service-armnn -v -c GpuAcc -n arm-armnn -a * Enabling fast_math may cause an increase in VTS or CTS test failures due to a change in precision Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: Ifd8931f95efd65d3ae3aca9d9d61bd381e4e24a5
2020-09-14IVGCVSW-5304 Remove boost::numeric_cast from Android-nn-driverMatthew Sloyan
* Replaced with armnn/utility/NumericCast.hpp Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: I6253261508e49ddeaa5ba3f3893a059486637467
2020-09-11IVGCVSW-5245 Support Fused Activations for Dynamic TensorsKevin May
* Move ProcessActivation from Convert<LayerName> to SetupAndTrackLayerOutputSlot by passing optional ActivationFn * Connect Activation after IsTensorInfoSet() is called Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: I472bcb65b12ae6e934bd1e9af8a6f6aceb311c0e
2020-09-08IVGCVSW-5270 Update ConvertConcatenation function to use ShapeInferenceMethodKeith Davis
Signed-off-by: Keith Davis <keith.davis@arm.com> Change-Id: I13e16d271ba55217b98a439aa82931f809fdeeb8
2020-09-03IVGCVSW-5274 'Update ConvertQuantizedLstm function to use ShapeInferenceMethod'Sadik Armagan
* Enabled Dynamic Tensors in QUANTIZED_LSTM operator. !android-nn-driver:3897 Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I415014d19729aac255479099e372e5ff1a6dd3e2
2020-09-03IVGCVSW-5271 'Update ConvertQuantized16BitLstm function to use ↵Sadik Armagan
ShapeInferenceMethod' * Enabled DynamicTensors on Quantized16BitLSTM operator. !android-nn-driver:3897 Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: Ic86c5af5a4d1b1d12fc6879dfb94fddd889b85de
2020-09-03IVGCVSW-5272 'Update ConvertLstm function to use ShapeInferenceMethod'Sadik Armagan
* Enabled Dynamic Tensors on LSTM operator Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I9cae539559570a44088a986870d3d3e41aee9468
2020-09-02IVGCVSW-5276 'Update ConvertSqueeze function to use ShapeInferenceMethod'Sadik Armagan
* Enabled dynamic type tensors on Squeeze operator in nn-driver. Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I2092cf6087da2821a07bd4743c4676d5afb35e66
2020-08-31IVGCVSW-4917 Adding Unit test to Android-nn-driver for Hal1.3 QosDavid Monahan
Signed-off-by: David Monahan <david.monahan@arm.com> Change-Id: Ie45464f2b04c8f2bb30ca06ff91b96492f2466b0
2020-08-28Remove mention of lack of support for HAL1.3 in GpuAccTeresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I2ac8b2dd1d012ddcd2f134f6d0d564f068caf601
2020-08-25Minor update to docs/FAQ.mdNikhil Raj
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: Ide62c0400cac372d5fac8d52ca61e7012447d396
2020-08-25Update Integrator guide in android nn driverNikhil Raj
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: I02d1ae8cc5b90ea4428af210f69d2358cdca3f6d
2020-08-21Update FAQ in android-nn-driverNikhil Raj
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: I95ceab4e545f760e1425b92e17d52a2248379d3c
2020-08-20IVGCVSW-4809 Update Nnapisupport.txtRyan OShea
* Update support for various layers Signed-off-by: Ryan OShea <Ryan.OShea2@arm.com> Change-Id: I17ebe45fdf065873e2c2fc661cbaf1ec2feb9b02
2020-08-20IVGCVSW-5220 Set all operations to unsupported after encountering an ↵Finn Williams
unsupported operation with with dynamic inputs Change-Id: Ia30698d608810dabb419d7d326ad985789d50603 Signed-off-by: Finn Williams <Finn.Williams@Arm.com>
2020-08-20IVGCVSW-5224 Fix for UnknownDimensionsTest in CpuRef and GpuAccKevin May
* Correctly handle HalOperandLifeTime::NO_VALUE in ConvertTranspose Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: I36790a90b5a3eac3da9e4edafc96387bb4375db9
2020-08-19IVGCVSW-5220 Fix UnknownCombinationsTest/UnknownDimensionsTestFinn Williams
Signed-off-by: Finn Williams <Finn.Williams@Arm.com> Change-Id: I4729497e67b711a8f1fbf7c555a26e97fa6c9ab6
2020-08-16IVGCVSW-5182 Bug fix for Comparison layer introduced by dynamic tensorsTeresa Charlin
* Addresses this error: Tried to connect an output slot to an input slot, but the latter already has a connection Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: Id011f4b42453b66bca2a388b8081151d74d006c3
2020-08-14IVGCVSW-5182 Update Convert functions to use ShapeInferenceMethod. 1/2.Teresa Charlin
* ConvertToActivation * ConvertAdd * ConvertArgMinMax * ConvertConv2d * ConvertDepthToSpace * ConvertDepthwiseConv2d * ConvertDiv * ConvertFloor * ConvertFullyConnected * ConvertL2Normalization * ConvertLocalResponseNormalization * ConvertMean * ConvertMul * ConvertPad * ConvertReshape * ConvertSub * ConvertStridedSlice * ConvertTranspose * ConvertBatchToSpaceNd * ConvertSpaceToBatchNd * ConvertComparison_1_2 * ConvertConv2d_1_2 * ConvertDepthwiseConv2d_1_2 * ConvertElementwiseUnary * ConvertExpandDims * ConvertGather * ConvertGroupedConv2d * ConvertInstanceNormalization * ConvertLogSoftmax * ConvertMaximum * ConvertMinimum * ConvertPadV2 * ConvertPrelu * ConvertQuantize * ConvertResize * ConvertSpaceToDepth * ConvertSoftmax * ConvertTransposeConv2d Signed-off-by: Finn Williams <Finn.Williams@Arm.com> Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: Idacf16e5eab56d83fce293570bbc89381ae056dc
2020-08-12IVGCVSW-4931 Update NN Driver to support dynamic tensorsFinn Williams
* Change NN Driver m_Network to now have ShapeInferenceMethod::InferAndValidate * Implement dynamic tensor support for: - ArgMinMax layer - Pooling2d layer - Activation layer * Skip dynamic tensor tests for any HAL other than 1.3 Change-Id: Icf66c968e49cdd4822b8c79c5f18b3f9e97dc53f Signed-off-by: Finn Williams <Finn.Williams@Arm.com> Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
2020-08-10IVGCVSW-3568 Eliminate rank and axis restriction in Softmax.Teresa Charlin
* Restriction in axis will be now part of ACL. Currently, ACL only supports axis = 0, which translates to axis = -1 in ArmNN and Android. * Beta must be Float16 when input/output are Float16 !armnn:3690 Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I2645a005840e17703367b3ec7e9ed91e83a2f6c7
2020-07-21IVGCVSW-4709 Re-enable Android-NN Resize ParametersDavid Monahan
* Re-enabled support for Align Corners and Half Pixel Centers Signed-off-by: David Monahan <david.monahan@arm.com> Change-Id: Iec8f5f5b5a1142547957ad9128037315b1da7935
2020-07-20IVGCVSW-4891 CTS Q 1.2 CpuRef LargeGraph_TENSOR_FLOAT16_Rank2/20 failure.Teresa Charlin
* Fp16 precision issue Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I61c9636afffca96f6a9f713d991598e04d0e50e6
generated by cgit v1.2.1 (git 2.23.0) at 2024-04-19 11:40:11 +0000