aboutsummaryrefslogtreecommitdiff
path: root/src/armnn/Network.cpp
AgeCommit message (Collapse)Author
2022-02-03IVGCVSW-6634 SubgraphView: Add method of returning a GetSubgraphWorkingCopyFrancis Murtagh
* Add pointer to SubgraphView allowing it to store a working copy implementation of its own representation of graph. * Make SubgraphView a friend of Graph to allow access to layers. * Add constructor to SubgraphView taking SubgraphViewWorkingCopyPtr * Rewrite Graph::SubstituteSubgraph for use on SubgraphView * Add GetWorkingCopy() method * Add tests for replacement of multiplication with DepthwiseConv2d * Check GetBackendHint() has value before passing to PrecompiledLayer * Add GetOwningIConnectableLayer to IInputSlot to allow traversing from IConnectableLayer->IOutputSlot->IInputSlot->IConnectableLayer Signed-off-by: Francis Murtagh <francis.murtagh@arm.com> Change-Id: Iaaef14448d8b73867eaee9d69f4f98d5d1bf171c
2022-01-14IVGCVSW-6633 SubgraphView uses IConnectableLayer rather than Layer in its ↵Francis Murtagh
m_Layers * Added IInputSlot, IOutputSlot and IConnectableLayer to SubgraphView * Deprecated old member functions * Removed deprecated calls in ArmNN * Added GetOwningIConnectableLayer function to IOutputSlot * Updates ArmNN Core Major version for IOutputSlot ABI break * Updated Minor version of TfliteParser, OnnxParser and Delegate Signed-off-by: Francis Murtagh <francis.murtagh@arm.com> Change-Id: I2a8611bfabf5ae09d3602fe6a4bef166e18117b9
2022-01-12Fix INetwork::AddPrecompiledLayer to take the CompiledBlobPtr by value ↵Cathal Corbett
rather than reference. Signed-off-by: Cathal Corbett <cathal.corbett@arm.com> Change-Id: I4057d2d6055220bb0d415a934ac09688b699b77c
2021-12-23IVGCVSW-6632 OptimizationViews: has INetwork rather than Graph for holding ↵Cathal Corbett
layers * Deprecate the GetGraph() function in OptimizationViews & remove/fix occurances where OptimizationViews.GetGraph() is called. * OptimizationViews has member INetworkPtr. * OptimizationViews has GetINetwork() method. * Unit test added to OptimizationViewsTests.cpp. Signed-off-by: Cathal Corbett <cathal.corbett@arm.com> Change-Id: Ifc1e53f1c34d786502279631942f0472f401038e
2021-12-15IVGCVSW-6626 Promote backend headers in backendCommon to armnn/backendsColm Donelan
Move the following header files from backendsCommon to armnn/backends. * MemCopyWorkload.hpp * TensorHandle.hpp * Workload.hpp * WorkloadData.hpp * WorkloadFactory.hpp Replace them with forwarding headers and a pragma deprecation message. Resolve the deprecation messages in Arm NN code. Signed-off-by: Colm Donelan <colm.donelan@arm.com> Change-Id: I47f116b30f86e478c9057795bc518c391a8ae514
2021-12-14IVGCVSW-6630 Add new method AddPrecompiledLayer() to INetworkCathal Corbett
* Add new method AddPrecompiledLayer() to INetwork with Comments noting it is for backend users. * Added unit test to SubgraphViewTests.cpp. * Bug fix and code refactor in Graph.cpp specifically around Graph::SubstituteSubgraph(SubgraphView& subgraph, IConnectableLayer* substituteLayer) Change-Id: If2d816e5109e48ce920bf92d8823b39130c23a16 Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
2021-12-08Add addition timing logging outputJan Eilers
* Adds ExecuteNetwork when building the delegate only * Adds timings to delegate subgraph creation * Adds executions times Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: Ieff2f67ea8dbb6c2a708f8810e84a20485b7a631
2021-12-08Add ModelOptions logging outputJan Eilers
Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: I1947924504c1308442b816cff513b2080ed3cc0d
2021-11-17IVGCVSW-6509 Front End + Reference Workload implementationTamás Nyíri
Subtask of story: IVGCVSW-6164 Add a Pooling3d FrontEnd and Ref Implementation * Add front end * Add reference workload * Add corresponding unit tests Change-Id: Icce4146dd0a06a1da46a2def00a82d343e171750 Signed-off-by: Tamas Nyiri <tamas.nyiri@arm.com>
2021-11-08IVGCVSW-6527 Support the new memory API in loaded networkFinn Williams
* enable external memory management for neon and ref backends * change m_TensorMemoryVector to hold shared pointers * change input layer backend Id to match backend id of connected layer Signed-off-by: Finn Williams <finn.williams@arm.com> Change-Id: I2216a724028312eb101b290df3f224177826b1a0
2021-10-28IVGCVSW-5636 'Implement NNAPI caching functions'Sadik Armagan
* Get number of inputs and outputs from optimized network. * Get number of cached files if backend supports caching. Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: Ie02ac123bb7df9b0593a2fe46b5bb564a5994780
2021-10-20Add ConstTensorsAsInput support for Conv3dMatthew Sloyan
* Constant weights and biases are now stored as Constant layers. * Updated Serializer, Deserializer and unit tests to reflect this. * Updated TfLiteParser. * Updated Ref backend to handle constant weights and bias as inputs rather than reading from member variables. * Added Conv3d EndToEnd test. * Added NCDHW DataLayout and unit tests. Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: I10cdd354ca5f1c748730f92ffdb36bf810f83c8e
2021-10-15Refactor: Profiler moved to GraphDerek Lamberti
* This is to enable later work to instrument the Optimizer. Signed-off-by: Derek Lamberti <derek.lamberti@arm.com> Change-Id: I2cf1fe022e0d100d6d8705adfbb8cab3ffc96a86
2021-10-15Profiling instrumentation throughout the OptimizerDerek Lamberti
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com> Change-Id: Ifcdafc12ca09455af2389bf84e34b6b87bbb0b15
2021-10-08IVGCVSW-6417: Catch AddFullyConnected API error when weights TensorInfo ↵Cathal Corbett
isn't set * Updated code in Graph.cpp InferTensorInfos() to be more descriptive. * Added method VerifyConstantLayerSetTensorInfo() in Graph.cpp/hpp to error when ConstantLayer TensorInfo is not set. * Updated Optimize() in Network.cpp to call VerifyConstantLayerSetTensorInfo(). * Added unit test with ConstantLayer TensorInfo not set to catch error in VerifyConstantLayerSetTensorInfo(). * Added comments around method VerifyConstantLayerSetTensorInfo(). Signed-off-by: Cathal Corbett <cathal.corbett@arm.com> Change-Id: I366596243f7c5823676222e2d0cce1335bc8c325
2021-10-02IVGCVSW-5985 Remove deprecated codeJan Eilers
* Removes deprecated AddLayer, IsLayerSupported functions * Marks the whole LayerVisitor class as deprecated not just the constructor. This required to wrap all Accept functions in a no deprecate macro because the LayerVisitor is used as a parameter in there * Removes usage of deprecated LayerVisitor and replaces it with ExecuteStrategy. This required a few structural changes in the unit tests * Adds a default implementation for IStrategy called StrategyBase * Changes pyarmnn to use non deprecated constructor for INetworkProperties and adds related unit test * Marks usage of deprecated code in pyarmnn as deprecated. This required to extend INetworkProperties to allow backwards compatibility * Removes deprecated functions from CpuAcc, GpuAcc and Ref backends Note: This patch breaks compatibility with backends that are not updated in this patch !android-nn-driver:6325 Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: Id13b6f37a74d26eadeda2da1dc92915e725ed5a5
2021-10-01IVGCVSW-6163 Add Conv3d FrontEnd and Ref ImplementationMatthew Sloyan
* Added front-end * Added Reference workload * Added Serializer & Deserializer support * Added unit tests * Added NDHWC DataLayout Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: Iec4d39e7433b5334d52fa44cf8efc6bcd39319d8
2021-09-24IVGCVSW-3705 Add Channel Shuffle Front end and Ref ImplementationSimon Obute
* Add front end * Add reference workload * Add unit tests * Add Serializer and Deserializer * Update ArmNN Versioning Signed-off-by: Simon Obute <simon.obute@arm.com> Change-Id: I9ac1f953af3974382eac8e8d62d794d2344e8f47
2021-08-20IVGCVSW-6294 Detect and remove extraneous fp16 conversion layersJan Eilers
Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: I69a6ceda0d3e8d39947df71a2ad0d365ac7767d8 Signed-off-by: Finn Williams <Finn.Williams@arm.com>
2021-08-10IVGCVSW-6289 Separate tensor shape inference and validation callsFinn Williams
* Pass m_shapeInferenceMethod to OptimizerOptions in ExecuteNetwork Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: I90280fb7629092d3b66e8a3968ca9e35a0df854a
2021-08-09IVGCVSW-6119 ConstTensorsAsInput: FullyConnected Bug FixMatthew Sloyan
* Updated FullyConnected layer member variables when cloning as some backends still require them. * Added SetConstant call when using deprecated AddFullyConnectedLayer method to ensure backwards compatibility. * Added SetConstant to SimpleSample to ensure it runs on all backends. Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: Ie7b4e4b868f23f8fcf9c41ffd12e2ea9ea53afca
2021-08-06Infer tensor shapes before graph optimizationFinn Williams
Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: I2a7a9b7b21848e2b3258788f06b01159f95a0d6c
2021-08-06IVGCVSW-6119 ConstTensorsAsInput: FullyConnectedMatthew Sloyan
* Constant weights and biases are now stored as Constant layers. * Updated Serializer, Deserializer and unit tests to reflect this. * Updated TfLiteDelegate, TfLiteParser and OnnxParser. * Updated Schema with IsConstant and ConstantTensorsAsInputs. * Updated Ref backend to handle constant weights and bias as inputs rather than reading from member variables. * Added dynamic or constant input EndToEnd tests. !android-nn-driver:5959 Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: Ibf3cf437df1100e4b322b0d303c575c6339f9696
2021-07-22MLCE-530 Add front end support for UnidirectionalSequenceLstm on ArmNNNarumol Prangnawarat
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: I57bcbdec3eb0155f41af0fe7d6abf9bac2ec86eb
2021-06-30IVGCVSW-6161 ConstTensorsAsInput: Optimizer - Redirect ConstTensor layer membersMatthew Sloyan
* Optimization that searches for layers with ConstantLayers as inputs. * The layer member variables are then redirected to these ConstantLayers. Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: I24a2bf0e8575b808343e0bbe3897b344e94796ad
2021-06-30IVGCVSW-6114 Create multiple LoadedNetworks from one OptimizedNetworkMike Kelly
* Added IOptimizedNetwork constructor that takes another IOptimizedNetwork and a ModelOptions. * Changed PreCompiledLayer to use shared_ptr rather than unique_ptr to store the PreCompiledObject (no interface changes). * Added unit tests to ensure that PreCompiledLayer::Clone() clones the pointer to the PreCompiledObject correctly. Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: I3ef56055e0d189ffce9e651882d34da16c70a240
2021-06-16MLCE-510 Add CpuRef Shape Operator to ArmNNKeith Davis
* Add front end * Add reference workload * Serialization/Deserialization * Add unit tests * Update ArmNN Versioning Signed-off-by: Keith Davis <keith.davis@arm.com> Change-Id: I6fcb1fa341d6f08dea4003b13544e6e9f53fefd3
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
2021-05-24IVGCVSW-6069 Fold PAD into Depthwise ConvolutionTeresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: Ib01629256309cfe17f341909d5b9bbbb09361422
2021-05-08IVGCVSW-5818 Enable import on GPUNarumol Prangnawarat
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: I4e4eb107aa2bfa09625840d738001f33152e6792
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
2021-04-21Fold 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
2021-04-12IVGCVSW-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
2021-04-07Fix 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
2021-03-25IVGCVSW-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
2021-02-15IVGCVSW-4873 Implement Pimpl Idiom for INetwork and IOptimizedNetworkFrancis Murtagh
!android-nn-driver:5042 Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: Ia1ce8b839e81b46428ba0f78463e085e5906958d Signed-off-by: Francis Murtagh <francis.murtagh@arm.com> Signed-off-by: Finn Williams <Finn.Williams@arm.com>
2021-02-12IVGCVSW-4893 Refactor ILayerVisitor using unified interface strategy.Finn Williams
Signed-off-by: Jan Eilers <jan.eilers@arm.com> Signed-off-by: Finn Williams <Finn.Williams@arm.com> Signed-off-by: Francis Murtagh <francis.murtagh@arm.com> Change-Id: Id7bc8255a8e3f9e5aac65d510bec8a559bf37246
2021-02-03backends/reference: Add ReduceSum operation supportSadik Armagan
This patch addes ReduceSum operation support for reference backend, which computes the sum of elements across dimensions of a tensor. Changelog v1: - Fix file header descriptions. Chagelog v2: - Fix line limit issue. - Fix type conversion issue. Changelog v3: - Remove tabs. - Modify newly added file headers. Changelog v4: - Symbol on header isn't allowed so drop it from newly added file headers. Changelog v5: - Remove tabs, fix the use of brackets and align lines correctly. Changelog v6: - Add serializer and deserializer support. Changelog v7: - Fix build error add missed code. Changelog v8: - Rename ReduceSumDecriptor to ReduceDescriptor - Update m_KeepDims field data type to bool on ReduceDescriptor - Add ReduceOperation field to ReduceDescriptor - Rename ReduceSumLayer to ReduceLayer - Update ReduceLayer to use ReduceDescriptor - Update ReduceLayer::ValidateTensorShapesFromInputs() function - Rename RefReduceSumWokload to RefReduceWorkload - Update workload to use ReduceDescriptor - Update workload to use Decoders and Encoders - Remove ReduceSum.hpp and ReduceSum.cpp - Added Reduce.hpp and Reduce.cpp - Move Mean.cpp (which is implementing REDUCE_MEAN) functionality to Reduce.cpp - Update RefMeanWorkload to call Reduce function with ReduceOperation::Mean argument - Remove Mean.hpp and Mean.cpp - Update the Serializer/Deserializer ArmnnSchema.fbs for ReduceLayer, ReduceDescriptor, and ReduceOperation - Update Serializer and Deserializer for serializing/parsing ReduceLayer - Added TfLiter parser Sum test for REDUCE_SUM operator - Make corresponding changes on front-end and Ref backend to support REDUCE_SUM operator Changelog v9: - Fixed build errors. Change-Id: I8c8e034f3df73f9565b3c18eff51ecca6c542195 Signed-off-by: Inki Dae <inki.dae@samsung.com> Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
2020-11-13IVGCVSW-5328-5329 Fuse ActivationMike Kelly
* 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
2020-11-09IVGCVSW-5091 Add Logical ops frontend and ref implJames Conroy
* 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
2020-11-08IVGCVSW-5315 Create FuseBatchNorm classMike Kelly
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: Id0625c58dbeea79874bf986b70d136ed9390bf83
2020-10-29IVGCVSW-5314 Create OptimizeForExclusiveConnectionTeresa Charlin
* FuseBatchNorm class has been added to facilitate testing * Only Convolution2D FP32 being fused Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I049c4770946ddca21b08516d4c9f4d0d22bf9b45
2020-10-13IVGCVSW-4489 Remove remaining occurrence of boost::formatMatthew Sloyan
* Replaced with fmt::format in Descriptors.cpp. * Removed remaining boost/format headers in ArmNN codebase. * Removed additional boost header in Network.cpp Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: Ib98b83bf4ec99ef98ce7a3635ec0dd478c3e43e1
2020-09-30Refactored Optimize(...) function to throw exceptions instead of returning nullMike Kelly
* INetwork::Optimize(...) states that the function should throw an exception if it fails but the implementation in Network.cpp returned null in some scenarios instead. This has led to some confusion amongst users. Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: I358d1293232c9464772aa0e39ab3355e3570c823
2020-09-17IVGCVSW-5303 Remove some boost::numeric_cast from rest of ArmNNMatthew Sloyan
* Replaced with armnn/utility/NumericCast.hpp * Exclusions in TypeUtils.cpp and QuantizerVisitor.cpp * Excluded as requires float implementation in NumericCast.hpp Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: I5c4c60e7028e1a51bf9379457278d253fd37bc70
2020-09-15IVGCVSW-5305 AddBroadcastReshapeLayer as optimizerNarumol Prangnawarat
* Remove AddBroadcastReshapeLayer from TfLiteParser * Add AddBroadcastReshapeLayer as optimizer * AddBroadcastReshapeLayer optimizer unit tests * Load-scope dynamic tensor broadcasting unit tests Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: I3549e85b71b41cbd4d96c0f1ece7887acbca76d1
2020-09-10IVGCVSW-5156 Introduce ModelOptions to OptimizedNetworkSadik Armagan
* 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
2020-09-08IVGCVSW-5244 Load-scope dynamic tensor TfLite testsNarumol Prangnawarat
* Infer tensor shapes at the beginning of Optimize function * Unit tests Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: I511f1228a12ebcad570e42a0c46d461ab9ccdc2c
generated by cgit v1.2.1 (git 2.23.0) at 2024-07-02 03:01:52 +0000