aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2021-05-18IVGCVSW-5964 Removing some remaining boost utility usages from tests.Colm Donelan
* Adding a basic PredicateResult class to replace boost::test_tools::predicate_result * Replacing all uses of boost::test_tools::predicate_result with the new armnn::PredicateResult class * Replacing use of boost::test_tools::output_test_stream output with std::ostringstream in ProfilerTests.cpp Signed-off-by: Colm Donelan <Colm.Donelan@arm.com> Change-Id: I75cdbbff98d984e26e4a50c125386b2988516fad
2021-05-14MLCE-500 Link zlib library to ArmNNKeith Davis
Signed-off-by: Keith Davis <keith.davis@arm.com> Change-Id: I7c47d0db778456380026cf56865e367e469067e3
2021-05-13IVGCVSW-6026 & IVGCVSW-6025 Delegate Unit Test Errors in ConsoleKevin May
* Remove unsupported Delegate Unit Tests for CAST and UNPACK Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: I03e460a77ee54e63e024d58e8f032246eaa9bac3
2021-05-13Github #330 Missing items on installationFrancis Murtagh
* Allow installation of ArmnnConverter Signed-off-by: Francis Murtagh <francis.murtagh@arm.com> Change-Id: I9deccb23b969c78d3e79b3a948498d2ec6fe6a5f
2021-05-12IVGCVSW-5722 Update README.mdNarumol Prangnawarat
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: Ib1d74d644be1738ea13c5f6b2d17b8411fb3f6ee
2021-05-12IVGCVSW-5622 Update cross compiling guide with note on the debian versions ↵Nikhil Raj
on host and target * Update android NDK guide to checkout ACL tag * Update cross-compiling guide with deprecated tools information Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: I1a2340003ac836a385a5ad73c5949c283e7aea84
2021-05-12IVGCVSW-5908 Update 21.05 Doxygen Documentsmathad01
* Increment ArmNN project version number. Signed-off-by: mathad01 <matthew.haddon@arm.com> Change-Id: Ieefb31f563d1db655268a41f4b31c28a93a54a48
2021-05-11IVGCVSW-5818 Unload network before checking result and improve testNarumol Prangnawarat
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: Ic29592f808352b8a240bdafa9f2f8a09a737acfd
2021-05-11IVGCVSW-6001 Fix CheckProfilingObjectUids test failing on Ubuntu 21.04Francis Murtagh
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com> Change-Id: I68a9397db974c91d29d6c8a8f9b5f7e32950f141
2021-05-10IVGCVSW-5970 - Add UNPACK and PACK to delegate documentationKevin May
Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: I59df474b957dc7f45aed3152174849c94769d7a0
2021-05-10IVGCVSW-5939 Fixing broken links in IntegrateDelegateIntoPython.mdColm Donelan
* Fixing broken links in IntegrateDelegateIntoPython.md * Adding TFLite Model Benchmark Tool to BuildGuidenative.md Signed-off-by: Colm Donelan <Colm.Donelan@arm.com> Change-Id: I41b7e1fb1dc7b5a95a5ab2a1ad2207150251e835
2021-05-10IVGCVSW-5808 Fix ArmNN backend profiling tests which fail on Jenkins with ↵Nikhil Raj
NPU enabled Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: Ie8f8d9d2dd65d85ed40529233ed45c09f862d602
2021-05-10IVGCVSW-5818 Add dma buf support for memory import on GPUNarumol Prangnawarat
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: Ia2d248d882111bb9f502cea4595cfd2569701f5d
2021-05-10IVGCVSW-5970 TfLiteDelegate: Add UNPACK operator SupportKevin May
Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: I23731718236043b46c143eaf416cb375edd93983
2021-05-08IVGCVSW-5818 Enable import on GPUNarumol Prangnawarat
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: I4e4eb107aa2bfa09625840d738001f33152e6792
2021-05-07Revert "MLCE-418 Reduce layer does not support multiple axes"Matthew Sloyan
This reverts commit d905decd256558bbee165e636ce4242ac3b9c917. Reason for revert: LargeGraph_TENSOR_FLOAT32/FLOAT16 CTS tests failures Change-Id: Ie69826549e73775825f45134375b5b2c41aebd01
2021-05-07IVGCVSW-5418 'ExecuteNetwork test for MobileBERT'Sadik Armagan
* Set the correct index for connecting constant layers. Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I86a626b82943e0d04b8ecb6b4f0f1b750b22d161
2021-05-07IVGCVSW-5987 Print Reduce Descriptor on dot graphTeresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I565a510de0dabdc25d518698174cd61d796239f4
2021-05-07MLECO-1252 ASR sample application using the public ArmNN C++ API.Éanna Ó Catháin
Change-Id: I98cd505b8772a8c8fa88308121bc94135bb45068 Signed-off-by: Éanna Ó Catháin <eanna.ocathain@arm.com>
2021-05-06IVGCVSW-5813 Add Async Queue to IRuntimeKeith Davis
Signed-off-by: Keith Davis <keith.davis@arm.com> Change-Id: Icc0d131c8ee2e9748e2f14762a75962b39c10f9d
2021-05-06MLCE-418 Reduce layer does not support multiple axesMatthew Sloyan
* Added backend specific optimization to chain new reduces layers for each axis to simulate behaviour of a layer with multiple axes. * Added function to calculate reduced output shape. * Added unit tests. Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: I180b0b111b7bcf3d0c283f1db0b82d5f17757682
2021-05-06IVGCVSW-5815 Generalise ConstCpuTensorHandleJames Conroy
* Generalises ConstCpuTensorHandle and inherited classes by removing 'Cpu' from aliases. * New renamed classes: ConstTensorHandle, TensorHandle, ScopedTensorHandle, PassthroughTensorHandle, ConstPassthroughTensorHandle. Signed-off-by: James Conroy <james.conroy@arm.com> Change-Id: I1824e0e134202735fb77051f20a7252f161dfe16
2021-05-06IVGCVSW-5969 TfLiteDelegate: Add PACK operator SupportMatthew Sloyan
* Added support for PACK which is equivalent to Arm NN STACK Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: I9ea134d0310eeea1caba30a8b9221712e9487c75
2021-05-06IVGCVSW-5410 Move ILayerSupport.hpp to backends folderFrancis Murtagh
* ILayerSupport is a backend interface, and so in order to prevent false positives in ABI Compliance Checker move it to backends folder. * Front end users should use ABI stable GetILayerSupportByBackendId which takes advantage of LayerSupportHandle Signed-off-by: Francis Murtagh <francis.murtagh@arm.com> Change-Id: Ie119451c5d55f114525dc79b6f3474b2df7e3418 !android-nn-driver:5516
2021-05-06Update ACL pin to branches/arm_compute_21_05Teresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: Ic41adf55d3a28b4e3042c7519314789a61949255
2021-05-06IVGCVSW-5418 'ExecuteNetwork test for MobileBERT'Sadik Armagan
* Refactored the code for checking constant inputs. * Added a unit test for ADD operator with constant input. Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: Ie7207e5a1ce77ea305552859de32a66e07c68a6f
2021-05-05Update guides with correct version of libprotobufNikhil Raj
* libprotobuf.23 is the correct version of protobuf 3.12 Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: I2dff2a2dcb48fc1038ef18f27d2aaee268710078
2021-05-05IVGCVSW-5418 ExecuteNetwork test for MobileBERTmathad01
* Fix bug in stack layer which causes mobileBERT model to seg fault when running in concurrent mode. Signed-off-by: mathad01 <matthew.haddon@arm.com> Change-Id: Ib2b73ffaa5b70147b837b7c764064e530baba637
2021-05-05IVGCVSW-5826 Add per channel testsJan Eilers
* with Conv2D for tflite parser and delegate * with TransposeConv for tflite parser Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: I8d1ed1f3388c6eace436d0e6fd5869451c6e7830
2021-05-05IVGCVSW-5882 Produce warning if bias quantization scale mismatchmathad01
* Changed behaviour of bias scale tolerance check such that if input quant * weight quant != bias quant +/- tolerance Then instead of throwing an error we send a warning. * Updated tests to reflect changes Signed-off-by: mathad01 <matthew.haddon@arm.com> Change-Id: Ifd97c574fe13805660df4636e9616b2d786b490d
2021-05-04IVGCVSW-5727 Implement Import function of ClImportTensorHandleDavid Monahan
* Split ClImportTensorHandle out from ClTenorHandle * Added implementation of Import function * Added Unit Tests Signed-off-by: David Monahan <david.monahan@arm.com> Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: I07de2ca5bebf19dfb9a8dddea4b18340ffc31fad
2021-05-04IVGCVSW-5882 Turn off Bias when data location equals -1mathad01
* Fix bug in stack layer which causes some models to seg fault. * Turn off bias input data if data location in TfLite file is set to -1. Signed-off-by: mathad01 <matthew.haddon@arm.com> Change-Id: I0db8cfe04874979382edcf2bed336339700e3538
2021-05-04IVGCVSW-5940 Enabling NN Driver dumps results in a driver segfaultMike Kelly
* Added checks to SerializerStrategy::CreateTensorInfo to handle situations where a shape has some unspecified dimensions Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: Idc64bfdabd5677c73a5c64f0c8e80156f3aae8e2
2021-04-29IVGCVSW-5819 5820 5821 Add MemorySourceFlags to ↵Francis Murtagh
TensorHandleFactoryRegistry::GetFactory * Modify Layer::CreateTensorHandles to include MemorySource * Modify INetworkProperties to add MemorySource * Disable Neon/Cl fallback tests until full import implementation complete Change-Id: Ia4fff6ea3d4bf6afca33aae358125ccaec7f9a38 Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
2021-04-29IVGCVSW-5890 Prevent modification to const layers with multiple connectionsColm Donelan
* In AddBroadcastReshapeLayerImpl check if a constant layer has other connections before modifying its output tensor shape. * In ElementWiseBaseLayer replace an ARMNN_ASSERT with a proper error message. Signed-off-by: Colm Donelan <Colm.Donelan@arm.com> Change-Id: Id3f3796c260eede61f076660505257a8b65d93fc
2021-04-29IVGCVSW-5744 Remove Tensorflow, Caffe and Quantizer from documentationKevin May
* Remove from .md files and Doxygen * Remove from armnn/docker build * Remove Tensorflow model format from ExecuteNetworkParams * Remove Tensorflow model format from ImageTensorGenerator Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: Id6ed4a7d90366c396e8e0395d0ce43a3bcddcee6
2021-04-29IVGCVSW-5775 'Add Async Support to ExecuteNetwork'Sadik Armagan
* Enabled async mode with '-n, concurrent' and 'simultaneous-iterations' in ExecuteNetwork * Number of input files provided should be equal to number of input files provided multiply by number of simultaneous iterations divided by comma !armnn:5443 Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: Ibeb318010430bf4ae61a02b18b1bf88f3657774c
2021-04-28IVGCVSW-4618 'Transition Units Test Suites'Sadik Armagan
* Moved doctest third-party library to armnn from delegate. License file is added. Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I4257c492ffd1c2d1b695ae4fc3ae70432acbaded
2021-04-28IVGCVSW-5843 Separate memory managers for WorkingMemHandlesFinn Williams
* Add inter layer memory management to WorkingMemHandle * Change Const layers to be executed once in loadedNetworkConstruction and share tensorHandle between all WorkingMemHandles * Fix various reference workloads pointing to memory in the queueDescriptor Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: I69d4b3c5c84d2f5abe4540c3e624ab4f00d88226
2021-04-28IVGCVSW-5831 Add additional options to Arm NN External DelegateMatthew Sloyan
* Added enable-fast-math and number-of-threads options. * Added save-cached-network and cached-network-filepath options. * Added external_delegate python tests for new options. Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: I7cf6522a6f895cd71ed8f369d94a5113d78594f9
2021-04-28IVGCVSW-5416 'Add android-nn-driver support for CASTSadik Armagan
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I02da912e5e4ca650b367ca40fe3f5ca5baa61cbb
2021-04-27IVGCVSW-5721 Remove the Tensorflow Parser from ArmNNNikhil Raj
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: Ida37d3ee3a1af0c75aa905199bd861726c646846
2021-04-27IVGCVSW-5719 Remove QuantizerKevin May
Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: I8a29df03afdd6f1cc8413b219e179272cd2d51cf
2021-04-27IVGCVSW-5714 Add example wav file for Wav2Letter GuideKevin May
* The wav file is a recording of the phrase "the quick brown fox jumps over the lazy dog" * This has been approved with legal Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: I8c3ba7d108623de94fb961e00f1dc34b78cd6452
2021-04-26IVGCVSW-5762 Update delegate build guide to remove tensorflow build.Colm Donelan
* Removed the build of tensorflow. * Fixed some build parameters. * Added minor fixes to improve usability. Signed-off-by: Colm Donelan <Colm.Donelan@arm.com> Change-Id: I9d03438ff8c3015c442d9662ae3d2b8e7cd58382
2021-04-23IVGCVSW-5430 'Add CAST Operator Support to Delegate'Sadik Armagan
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I6da711950b8e7d3c0d5cbd443e91eb36700ac4c8
2021-04-22IVGCVSW-5419 'Add ACL Support for CAST Operator'Sadik Armagan
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I481343af311cf3cbc81eee80e80d8b5581fdfd7b
2021-04-22IVGCVSW-5420 'Add CL support for CAST'Sadik Armagan
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I1bbf1f2edf7282cb69b99e22de1b8a2fe6e443c2
2021-04-22IVGCVSW-5418 ExecuteNetwork test for MobileBERTmathad01
* Removed check in TfLiteParser and Delegate that requires both weights and biases to be constant or non-constant simultaneously * Updated TfLiteParser FullyConnected layer test to properly use non-constant weights * MobileBERT Float32 model now runs on TfLiteParser Signed-off-by: mathad01 <matthew.haddon@arm.com> Change-Id: I1d75eea466caa90cd695ad353160362df2f69483
2021-04-21IVGCVSW-5909 Fix CTS failure in GpuAcc DIV int32Teresa Charlin
* CLWorkload was only supporting float Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: Ic57a490f03a055c158edc19e831b153a44e25166
generated by cgit v1.2.1 (git 2.23.0) at 2024-07-08 23:04:41 +0000