aboutsummaryrefslogtreecommitdiff
path: root/src/armnn
AgeCommit message (Collapse)Author
2021-06-16IVGCVSW-5826 Change weights layout for depthwise to [1,H,W,I*M]Jan Eilers
* This change is necessary because tflite uses a [1,H,W,I*M] format and uses the I*M dimension for per axis quantization. Our previous layout [M,I,H,W] can't handle the correlating quantization scales. * Updates Onnx-, TfLiteParser and TfliteDelegate * Updates the CpuRef, CpuAcc and GpuAcc backends * Adjusts unit tests * Adds test to ensure models with old layout can still be read and executed * Adds conversion function to previous layout [1,H,W,I*M] --> [M,I,H,W] which can be used by backend developers !android-nn-driver:5553 Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: Ifef23368b8c3702cf315a5838d214f7dc13c0152
2021-06-16IVGCVSW-5835 Move the src/profiling/LabelsAndEventClasses class to ↵Nikhil Raj
profiling/common Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: I83de0fe9c83ec7e698817095ce5cfe3319c36ea6
2021-06-11IVGCVSW-5963 'Move unit tests to new framework'Sadik Armagan
* Used doctest in ArmNN unit tests Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: Ia9cf5fc72775878885c5f864abf2c56b3a935f1a
2021-06-09IVGCVSW-5855 Refactor the reporting of capabilities from backendsFinn Williams
Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: I05fc331a8e91bdcb6b8a2f32cfb555060fc5d797
2021-06-04COMPMID-4548 Print Elementwise Descriptor on dot graphTeresa Charlin
*Order the functions alphabetically Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: Ia19f2727733026aefab17ebce0cabb66863a7af7
2021-06-02IVGCVSW-5962 Remove boost::multi_arraySadik Armagan
* Replaced all instances of boost::multi_array with flat vectors. * Updated LayerTestResult struct with new member variables. * Updated CompareTensor function to compare flat vectors and the shape. * Removed MakeTensor function from TensorHelpers.hpp. * Removed GetTensorShapeAsArray function from LayerTestResult.hpp. * Removed boost::array usage. * Removed boost::extents usages. * Removed boost::random usages. Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: Iccde9d6640b534940292ff048fb80c00b38c4743
2021-06-02COMPMID-4544 Print Comparison Descriptor on dot graphTeresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I01ef1dda44e5c6e6a71a6fcd49486e2135dc1822
2021-06-01IVGCVSW-5833 Move the ProfilingGuid out of Types.hpp to its own header in ↵Nikhil Raj
profiling common !android-nn-driver:5691 Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: Ib71af0831e324ac6bd27b1a36f4a6ec1a703b14a
2021-05-31IVGCVSW-6059 Fixing PermutationVector.end() to cope with dimensions < 5Colm Donelan
* PermutationVector.end() was returning the end of the fixed size array m_DimMappings rather than the number of mappings set by the constructor. Signed-off-by: Colm Donelan <Colm.Donelan@arm.com> Change-Id: Ie218f7922e8c9c35c1dc702e43a5ee2fd1a61ff0
2021-05-27IVGCVSW-5781 Ensure Threadpool Memhandles are created after constant layer ↵Finn Williams
allocations Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: If20572706d14df05e6d95ba436b364876d839495
2021-05-26IVGCVSW-6009 Enable creating thread pool with 1 threadKevin May
* Allow the user to use create a tread pool with a single thread * This is in keeping with how the android-nn-driver was implemented * Add it to ExecuteNetwork thread pool creation Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: I05b8048a9e0e45ae11d2b585080af28d9d008d81
2021-05-26IVGCVSW-6009 Integrate threadpool into ExNetKevin May
* Remove concurrent flag from ExecuteNetwork as it is possible to deduce if SimultaneousIterations > 1 * Add void RunAsync() * Refactor some unit tests Change-Id: I7021d4821b0e460470908294cbd9462850e8b361 Signed-off-by: Keith Davis <keith.davis@arm.com> Signed-off-by: Kevin May <kevin.may@arm.com>
2021-05-25IVGCVSW-3649 Add Prelu with different alpha dimension test to TfLiteParserNarumol Prangnawarat
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: I982ecd66ea3ed4d88934cd8254832eecb4a7adb4
2021-05-24IVGCVSW-6069 Add Unit Test for Pad + DepthwiseConv and Pad + ConvTeresa Charlin
*All fold pad test are now in a separate file Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: Ic0b0436f6b0194404f9a3f1553e2f69524b63580
2021-05-24IVGCVSW-6069 Fold PAD into Depthwise ConvolutionTeresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: Ib01629256309cfe17f341909d5b9bbbb09361422
2021-05-20MLCE-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. * Includes rework to fix IVGCVSW-5987. Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: I154b3698b5e6756b05b2a0b5a3f0896184efce72
2021-05-18IVGCVSW-5964 As part of Boost removal this Windows only code is obsolete.Colm Donelan
This block of code to help our Windows user is no longer relevant with the removal of Boost. Signed-off-by: Colm Donelan <Colm.Donelan@arm.com> Change-Id: I0f63277cd6913b8edfbcccf3f2cd1880227c35ec
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
2021-05-08IVGCVSW-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-5987 Print Reduce Descriptor on dot graphTeresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I565a510de0dabdc25d518698174cd61d796239f4
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-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
2021-04-29IVGCVSW-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-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
2021-04-27IVGCVSW-5719 Remove QuantizerKevin May
Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: I8a29df03afdd6f1cc8413b219e179272cd2d51cf
2021-04-21Fold PAD into Pooling2d if possibleDiego Lopez Recas
Some models would add a PAD layer before a pooling when they can't express their padding configuration as SAME or VALID. ArmNN can potentially merge the two merge the two because pooling layers are described with explicit padding. The merge is possible if the extra padding is neutral in the combined pooling operation. A merged operation can only fuse paddings in the dimensions that accept explicit padding in a pooling operation, i.e. the spatial dimensions. Signed-off-by: Diego Lopez Recas <diego.lopez.recas@gmail.com> Signed-off-by: Colm Donelan <Colm.Donelan@arm.com> Change-Id: Icd54718dcd9e797c923456b7fa6e0213e288e668
2021-04-21IVGCVSW-5842 Remove cross-wiring in depthwiseJan Eilers
* Reading tensor infos won't allow a permutation vector anymore. The permutation only changed the quantization dimension not the shape and was therefore misleading * The permutation of the full tensor info is now performed in armnnUtils::Permuted * Changed TfLite Parser depthwise parsing function * Added unit tests to TfLite Parser with more random data * Changed TfLite Delegate depthwise parsing function * Added unit test to the delegate with per channel quantization !android-nn-driver:5412 Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: I1f985ee69547bcaf16a72201e00a6b6fe1ef9a97
2021-04-20IVGCVSW-5816 Constant memory accessFrancis Murtagh
* Add new class ManagedConstTensorHandle to Unmap when out of scope * Integrate into existing layers that have constants * Add unit tests Signed-off-by: Francis Murtagh <francis.murtagh@arm.com> Change-Id: I0a05e14e438804b37e9862e76b5ca329483f6b45
2021-04-12IVGCVSW-5410 Add front-end support for CASTmathad01
IVGCVSW-5415 Add TfLiteParser support for CAST * Added front end support for CAST, including support in the Reference workload, Serialization, Deserializtion, Unit tests, and TfLiteParser. Signed-off-by: mathad01 <matthew.haddon@arm.com> Change-Id: Iaf670ca5912a21ed6bc84f7f83a68b42154846bb
2021-04-09MLCE-328 Serializer/Deserializer does not support Signed64Mike Kelly
* Added support for Signed64 to flatbuffer's schema & updated source tree * Added support for Signed64 to TFLite Delegate * Added support for Signed64 to Serializer * Added support for Signed64 to Deserializer * Added unit test for ArgMinMax to Deserializer * Deprecated m_Output_Type from the ArgMinMaxDescriptor: the output type is solely determined by the DataType of the output Tensor * Fixed issue where RefArgMinMaxWorkload could output data using the wrong DataType * Added Signed64 to RefLayerSupport::IsArgMinMaxSupported as a supported type Signed-off-by: Mike Kelly <mike.kelly@arm.com> Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: Ib622c052a1f8aa3e658262f8bde5a6881a8cbe10
2021-04-08IVGCVSW-5823 Refactor Async Network APIMike Kelly
* Moved IAsyncNetwork into IRuntime. * All LoadedNetworks can be executed Asynchronously. Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: Ibbc901ab9110dc2f881425b75489bccf9ad54169
2021-04-07Fix graph copy memory spikeFinn Williams
* Change layer storage of ConstTensors to std::shared_ptr<ConstCpuTensorHandle> * Change clone to share ConstTensor rather than copy * Remove uses of non-const GetTensor() call * Reduce scope of non-optimized network in ExeNet, so memory can be released after use Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: Ibb2c7309d12411d21405bd6024c76bcdf5404545
2021-04-02IVGCVSW-5783 'Add AsyncExecution Capability'Sadik Armagan
* Added AsyncExecution to the BackendCapability enum class. * Logged a warning if backends do not support AsyncExecution capability if AsyncNetwork is created. Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I49f8467297f4b6b8e414cb6a3638a7d3f1bb886a
2021-03-30IVGCVSW-5799 'Create Pimpl Idiom for Async prototype'Sadik Armagan
* Implemented Pimpl Idiom for IAsyncNetwork Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: Ic7311880563568b014a27f6347f8d41f2ad96df6
2021-03-29IVGCVSW-5790 Merge async prototypeMike Kelly
* Added thread safe execution mechanism for armnn * Removed duplicate function bool Compare(T a, T b, float tolerance) * Added StridedSliceAsyncEndToEndTest * Fixed memory leak Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: I2d367fc77ee7c01b8953138543e76af5e691211f
2021-03-25IVGCVSW-5736 and IVGCVSW-5743 'NonConstWeights: Update front-end and ↵Sadik Armagan
TfLiteDelegate support for FullyConnected Operator' * Added front-end support for non-const weights for FULLY_CONNECTED operator * Added FULLY_CONNECTED end-to-end test * Updated FULLY_CONNECTED operator support in TfLite Arm NN Delegate for non-const weights * Updated the version numbers Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: Iffa5b9aa9297aca4c02d923cce4636c88ac21faa
2021-03-23Revert "Fold PAD into Pooling2d"Jim Flynn
This reverts commit 51ce7d487c761358de105f82ff90553570aedac0. Reason for revert: https://jira.arm.com/browse/IVGCVSW-5798 LargeGraph_TENSOR_FLOAT32 CTS tests failures Change-Id: Ib031a47f605340b2202ecf074ce96a8b54c51075
2021-03-22Fold PAD into Pooling2dDiego Lopez Recas
Some models would add a PAD layer before a pooling when they can't express their padding configuration as SAME or VALID. Arm NN can merge the two because pooling layers are described with explicit padding. Signed-off-by: Diego Lopez Recas <diego.lopez.recas@gmail.com> Change-Id: Id048186db6a005e0257bfbc1406c3b0dab2cdd58
2021-03-16IVGCVSW-5754 Change the behaviour of the AddBroadcastReshapeLayer ↵Finn Williams
Optimisation when the input is a const tensor Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: I8b1357bdefc45880d064d7e448af364ac8644c0d
2021-03-12IVGCVSW-5767 'Regression on SqueezeNet v1.1'Sadik Armagan
* Update ReduceLayer to use descriptor parameters Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I2ff240f63534de0fd647428cf411763829412443
2021-03-03IVGCVSW-5612 Fix tiny_wav2letter_relu_fixed_int8 delegate outputexperimental/abi-testsFinn Williams
* fix delegate perchannel quantization * change delegate to check reshape options before inputs * Add int8 "qsymms8" option to ExecuteNetwork * Add option to run ExecuteNetwork on tflite w/o delegate !referencetests:301301 Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: If3e12599b17aff1199d7ab0a55e1c901e480083d
2021-03-01Make SubgraphViewSelector give deterministic resultsRob Hughes
The subgraphs produced by SubgraphViewSelector were not deterministic as the order of the input slots, outputs slots and layers within each subgraph were determined by the pointer values of those objects, which are not guaranteed to be the same for each execution. This patch adds a post-processing sorting step based on the GUIDs of the layers and the slot indices so that the results will be the same for each execution. This makes debugging the optimised graph much easier as subsequent stages can also be deterministic. Change-Id: Ifbcb199733066f99e9f95808a8da22023e5944f1 Signed-off-by: Rob Hughes <robert.hughes@arm.com>
2021-02-19Give unique names to debug layersRob Hughes
Debug layers are given names based on the layer they take their input from. If a layer has multiple outputs then one debug layer will be attached to each output. Therefore all these debug layers would have identical names making them hard to distinguish when debugging. This patch includes the output slot index which the debug layer takes its input from when creating the name. Change-Id: I09eaa8a7edad9bfdf678b4778cf740340013126c Signed-off-by: Rob Hughes <robert.hughes@arm.com>
2021-02-17IVGCVSW-5734 Building armnn failed in our Backends CI jobFrancis Murtagh
* CreateTestNetwork() and CreateTransposeTestNetwork should only be defined if Ref enabled; the same as the test its called in otherwise it's defined but not called. Signed-off-by: Francis Murtagh <francis.murtagh@arm.com> Change-Id: I7bc522a7884d216d1a8e51afd7cec7a66e4e2947
generated by cgit v1.2.1 (git 2.23.0) at 2024-07-06 20:46:03 +0000