aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2020-02-28IVGCVSW-4525 Adding TPIP comments to sourcev20.02branches/android-nn-driver_20_02Jan Eilers
Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: I4cd521f01172889966e64d03cdf899a355bd39d3
2020-02-26Update IntegratorGuide.md fileNikhil Raj
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: I901b8529f0bdfa281348853ad8ea944d2bcf01b9
2020-02-21IVGCVSW-4471 ValidationTestIntrospection.DeviceGetType fails in Q NN testsSadik Armagan
* Throw an exception if there is no known backend specified for the driver Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I8b0be33c0a8786b493ac1f8c17573853db8e8218
2020-02-21IVGCVSW-4375 Fixed driver crashesMike Kelly
* Fixed driver crashes caused by ignoring the result of GetTensorInt32Values. * Fixed driver crashes where padding, axis, permutation dimension or block size operands were inputs. Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: I59867e9545a240e6be46b7f68da6adaa120a56d8
2020-02-21IVGCVSW-4432 Update Readme for 20.02Sadik Armagan
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: Iac553b5b6b3890a13aa617bc64cbe626967e6d2b
2020-02-20IVGCVSW-4430 Update NNAPISupport.txt for 20.02Sadik Armagan
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: If475b0448a1adaa7c08cbdaa5efed1e0eae3c89a
2020-02-11Partial Revert "IVGCVSW-4130 Remove clframework from android-nn-driver build."Mike Kelly
* Partial reversion to restore Android.mk files. * Changed armnn-arm_compute library name to arm_compute_library. !armnn:2714 This reverts commit 826dd41dc4de616059a61fb0aaec432311372c6c. Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: Idb4a2eeb6cbb19a249c1a85eec2cf597d6b6d970
2020-02-10IVGCVSW-3987 Add armnn::Exception warning and std::exception errorKevin May
Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: I4963fb4d44501287e161f7366f38557962d06cac
2020-01-31IVGCVSW-4130 Remove clframework from android-nn-driver build.Colm Donelan
Signed-off-by: Colm Donelan <colm.donelan@arm.com> Change-Id: I019bdab899de19c1a2cb6bbd72dd38ceb677d98b
2020-01-31IVGCVSW-4388 Update ACL pinTeresa Charlin
* Update Android.bp file with new created files. !armnn:2672 Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: Ic56c041018073679c10074ea4c5e95eb7525a631
2020-01-28MLCE-153 Padding calculation for TransposeConv ignores strideMike Kelly
* Changed ConvertTransposeConv2d to use the unsigned values for strideX and strideY not the signed values from the descriptor. !ComputeLibrary:2599 !armnn:2612 Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: Iee300041f3ed585820b7c7e2edd8ab541f339d59
2020-01-28IVGCVSW-4360 Update ACL pinSadik Armagan
* Update Android.bp file with new created files. !armnn:2612 Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: Idedc9cc3f4bbdb99c29cd1ba0f355aae870fe2e5
2020-01-27IVGCVSW-4301 Correctly validate reshape for broadcastable inputsDerek Lamberti
!android-nn-driver:2642 Signed-off-by: Derek Lamberti <derek.lamberti@arm.com> Change-Id: I4db6ea4ed0a192c85f124c4a9ced60b1666a3870 Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
2020-01-24IVGCVSW-4262 Add Calls to IsReshapeSupported and IsPermuteSupportedKevin May
!armnn:2643 * Add calls before addition of these layers in ConvertConcatenation * Add outputInfo parameter wherever needed for IsReshapeSupported Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: Ic5d142ea046161960ff2fc137bd261ebb4e6ac0c
2020-01-24IVGCVSW-4270 Change .dot file name to start with netIdJim Flynn
* .dot file will start with the same number as the associated input and output tensor dump files Change-Id: Ic64539854c2b8c34a7034fa18a142b2dfe67df7d Signed-off-by: Jim Flynn <jim.flynn@arm.com> IVGCVSW-4271 Add getSupportedOperations marker file * Also fix segfault in previous graph dump code Change-Id: I01915f47ae17d89ad3595430d073a17b1a1fda58 Signed-off-by: Jim Flynn <jim.flynn@arm.com>
2020-01-24IVGCVSW-4260 Fix Transpose CpuRef VTS failuresJames Conroy
* Adds missing conversion for permutation vector from ANN/TF/Numpy format to ArmNN format. * Corrects legacy tests based on incorrect permutation vectors. Signed-off-by: James Conroy <james.conroy@arm.com> Change-Id: I767142378055e484d22f3ffba34580c528370cfe
2020-01-23IVGCVSW-4266 Dump float16 input/output tensorsJim Flynn
Change-Id: Iff91ce6857a9f96a7af65f79883c1cbe59a15dd2 Signed-off-by: Jim Flynn <jim.flynn@arm.com>
2020-01-23IVGCVSW-4370 Remove use of deprecated per-axis typeDerek Lamberti
!armnn:2620 Signed-off-by: Derek Lamberti <derek.lamberti@arm.com> Change-Id: I8d71bac981a7576c7f51783833f76151495c62c0
2020-01-13IVGCVSW-3813 Add Unary Elementwise Operation support to the android-nn-driverjosh minor
* Account for deprecated Abs and Rsqrt layers in ArmNN * Update HAL 1.2 * Neg HAL operation support added !armnn:2542 Signed-off-by: josh minor <josh.minor@arm.com> Change-Id: I043bf64ac7ed3aea65560d72acf664e079917baf Signed-off-by: josh minor <josh.minor@arm.com>
2020-01-13Rename quantized data typesDerek Lamberti
!armnn:2571 Signed-off-by: Derek Lamberti <derek.lamberti@arm.com> Change-Id: I06977553a097479a2a996e76a106249673d31ed7
2020-01-09IVGCVSW-4315 Fix Fully Connected infer output shape bugFinnWilliamsArm
Change-Id: If4fd1abdedf7de2046435d418fb1ee95ceb73419 Signed-off-by: FinnWilliamsArm <Finn.Williams@Arm.com>
2020-01-07IVGCVSW-4192 Add DEQUANTIZE to the android-nn-driverKeith Davis
* Support for QSymm8 in ConversionUtils.hpp Signed-off-by: Keith Davis <keith.davis@arm.com> Change-Id: I39c654e7a3821ffe74336a13bf0b922686f337d1
2019-12-19IVGCVSW-4181 Add RESIZE_NEAREST_NEIGHBOUR to the android_nn_driverKeith Davis
* Add FP16 support Signed-off-by: Keith Davis <keith.davis@arm.com> Change-Id: I59a2862c734aa3678f19cc47f024f8cb92fb557e
2019-12-13MLCE-133: Driver infers scratchBuffer shape.Pablo Tello
Change-Id: I7977d697772349b8ea7eb300937409ce0a3a4dee Signed-off-by: Pablo Tello <pablo.tello@arm.com>
2019-12-06IVGCVSW-4211 Rename QuantisedSymm8 to QSymmS8experimental/resizeCheckFinnWilliamsArm
!armnn:2421 Signed-off-by: FinnWilliamsArm <Finn.Williams@Arm.com> Change-Id: I30da5235f6610306f9300b4532cf2c79ee8789f8
2019-12-06IVGCVSW-4225 Reject dynamic tensors to TRANSPOSEMatthew Bentham
Signed-off-by: Matthew Bentham <Matthew.Bentham@arm.com> Change-Id: I1038d4f3c73d4e306161459784a0abf20d7e507d
2019-12-05IVGCVSW-4041 Adding Instance Normalization issue to FAQMike Kelly
* Added note to explain Instance Normalization failures to the FAQ. Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: Ie1361ece06c6f10d6faac2dd6e480393ab1b2f77
2019-12-05MLCE-149 Failure to build armnn 19.08 obtained from githubMike Kelly
* Updated FAQ to include instructions on resolving version incompatibilities between android-nn-driver, armnn and clframework. Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: I5f358d7241b9120c6896b8b8b38c89246e6573b1
2019-12-02IVGCVSW-4209 Remove the Half.hpp header usage from the driverMatteo Martincigh
* Removed the inclusion of the Half.hpp header from the Android NN Driver, as it's a private header not part of the now public armnnUtils API * Refactored the code not to use that header Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com> Change-Id: I0feeb86ccb31e016395e623029974f599a174149
2019-11-29Catch std::exception instead of armnn::ExceptionDerek Lamberti
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com> Change-Id: I89ae4f3b607ccb83f1bf16e085c805d5fc5cf89c
2019-11-28IVGCVSW-4209 Create a public API for the ArmNN UtilsMatteo Martincigh
* Using the new public armnnUtils API !armnn:2386 Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com> Change-Id: Ifa8af20ca131b1be19dbdceea6674a1274a396f3
2019-11-27MLCE-115 Remove redundant support checking for PermuteMatthew Bentham
This should all be done in the LayerSupport mechanism in Arm NN now. Change-Id: Icbbb1be2efad2ababf8bdd5543f3e5a06958dccd Signed-off-by: Matthew Bentham <Matthew.Bentham@arm.com>
2019-11-27IVGCVSW-4204 Review NNAPISupport.txt for 19.11Teresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I56959a6fd296781d4604c55179471299c321153e
2019-11-25MLCE-144 Fix 2d pooling convert functionFinnWilliamsArm
Signed-off-by: FinnWilliamsArm <Finn.Williams@Arm.com> Change-Id: I999d9091bc4046861433d4eb3109fe972611bd82
2019-11-25Refactor DequantizeIfRequired()Aron Virginas-Tar
* Added DequantizeStatus enum to capture the status of the dequantization process * Added alias DequantizeResult for the return tuple * Renamed instances of Operand, Operation and Model template variables to HalOperand, HalOperation and HalModel for consistency across ConversionUtils Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I2d5cf0dd9f9baba95684bb0b9fe20e63c0f377a3
2019-11-21Add FAQ for android-nn-driver, refactor READMEMatthew Bentham
Change-Id: I118cfe12e24b689539c634625910fb007cc436b6
2019-11-21IVGCVSW-4151 HAL 1_2 Dequantize FP32 Per Channel Tests on CpuAcc FailingSadik Armagan
* Quantization dimension other than 0 is not supported. Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: Ied3914600a754b799e98d5660ad6196c8c4fa23d
2019-11-19IVGCVSW-3697 Add Support for ANEURALNETWORKS_ARG[MAX|MIN] to HAL 1.2 DriverFrancis Murtagh
!armnn:2313 Signed-off-by: Francis Murtagh <francis.murtagh@arm.com> Change-Id: I543136e4e2ef9aece1378d2642064cc585246645
2019-11-19MLCE-144 Cts NNAPI test cases failedMike Kelly
* Fixed numerous CTS/VTS failures related to Quantization !armnn:2316 Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: I50b7edf42e416abd230783a5081d1a6511bc42d4
2019-11-18IVGCVSW-4137 Failing LSTM android-nn-driver Unit Tests in HAL 1.2Sadik Armagan
* Fixed for failing LSTM unit tests Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I773c5227bc8d5606924cc0472c51172476773056
2019-11-18IVGCVSW-4056 Update NNAPISupport.txt for 19.11Aron Virginas-Tar
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I3e8069d6cb4a2149396329fee4643d0fc5a12181
2019-11-18IVGCVSW-4139 Fix regression in ConvertDequantize()Aron Virginas-Tar
* Removed TENSOR_QUANT8_SYMM from the list of generally supported tensor data types * Fixed tensor info in DequantizeIfRequired() for on the fly dequantized QSymm8 weights * Moved code for checking whether a Dequantize operator is linked to FullyConnected or Lstm weights from ConvertDequantize() into a separate function inside 1.2/HalPolicy.cpp Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I19ea6f89a90f553a964b87d44f8ad8a064e96f7f
2019-11-15IVGCVSW-4082 Document support of per-axis quantisationTeresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I344dcf039e68297bc927dcb2b3f7f0f59398be5e
2019-11-15IVGCVSW-4115 Fix for armnn-driver-tests Capabilities failureKevin May
* Add TensorQuant8SymmPerChannel to ArmnnDriverImpl::getCapabilities_1_2 * Add TensorQuant8Symm and TensorQuant8SymmPerChannel to Capabilities supported operands tests Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: Ifbc742c5562f243172d2f4e6a2f6a8f3b6a405ea
2019-11-13IVGCVSW-4051 Update ACL pin to 94e0cf960ea6116eb57fa88d9b951f859b52c602James Conroy
!armnn:2211 Signed-off-by: James Conroy <james.conroy@arm.com> Change-Id: I248bfb6a45c90f053a849f38607a4ba6c14f39d1
2019-11-12IVGCVSW-4079 Modify the channel dimension accordingly with the weights ↵Teresa Charlin
permutation Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: Ie4a27d805d6d953fc54264ef9a0947f82c5b1ff8
2019-11-08IVGCVSW-4069 Add ProfilingGuid to Networkjaneil01
!armnn:2232 Signed-off-by: janeil01 <jan.eilers@arm.com> Change-Id: Ib24989dba72a9f9acd1c8017c1f39c3ee74030ea
2019-11-08IVGCVSW-3987 Fix for potential unique_ptr.release() bugKevin May
* Use an android strong pointer instead of a unique_ptr to avoid undefined behaviour of releasing unique_ptr to strong pointer Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: Icac255ba2407796888f20ffaba99a7988cb6f63c
2019-11-07IVGCVSW-4104 Support per-axis quantization for GROUPED_CONV2DAron Virginas-Tar
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: Ice7c4d3273db31130ec64edc1b76d1c9d5197961
2019-11-07IVGCVSW-4104 Skip per-axis quantization VTS/NeruralNetworks tests for ↵Aron Virginas-Tar
GROUPED_CONV2D * Report per-axis quantization as unsupported in ConvertGroupedConv2d() until support will have been added Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: Ibadb848b60956f8c90fa8b538d50dea8d9a57d92