aboutsummaryrefslogtreecommitdiff
path: root/tests/ExecuteNetwork
AgeCommit message (Collapse)Author
2023-04-26Update cxxopts from 3.0 to 3.1.1Jim Flynn
!android-nn-driver:9431 Signed-off-by: Jim Flynn <jim.flynn@arm.com> Change-Id: I58143445b5c5cf2aafd0838156c9543adce21e6a
2023-04-12IVGCVSW-7197 Implement Pimpl Idiom for OptimizerOptionsJohn Mcloughlin
Signed-off-by: John Mcloughlin <john.mcloughlin@arm.com> Change-Id: Id4bdc31e3e6f18ccaef232c29a2d2825c915b21c
2023-04-05IVGCVSW-6681 Improve error handling in TfLiteExecutor.Colm Donelan
The initial model load and tensor allocation operations against the TfLiteInterpreter were not checking return codes resulting in segmentation faults. Signed-off-by: Colm Donelan <colm.donelan@arm.com> Change-Id: I812785f0af9012c97570065d200f72eaf781165a
2023-03-06Fixing compare output feature in ExecuteNetworkColm Donelan
The -A -B -C options in execute network were attempting to calculate the RMS error over output tensors. However, the calculation was mixing tensor elements and bytes when doing the calculation. This patch changes the calculation to use a per byte RMS error calculation. Signed-off-by: Colm Donelan <colm.donelan@arm.com> Change-Id: If30230a16cfed1a8804b4d54ed1abcd371f26664
2023-02-06IVGCVSW-7476 Remove ProfilingOptions from DelegateOptions.Colm Donelan
ProfilingOptions is not used in DelegateOptions. Instead the parameters are passed in through the RuntimeOptions. This is done in ExecuteNetwork and TfliteExecutor. Signed-off-by: Colm Donelan <colm.donelan@arm.com> Change-Id: Iaab3d4ef277c47e1ff82a51ba2648f5f51ec3e2c
2023-01-31Fix for ExecuteNetwork Delegate when output is booleanRyan OShea
* When the output of a network is a boolean from a comparison layer ExecuteNetwork was missing the data type when writing the output tensor Signed-off-by: Ryan OShea <ryan.oshea3@arm.com> Change-Id: Id9c1609462395a68e8c1842c77a4a033a10f74e8
2023-01-27IVGCVSW-7441 Checking for constant input tensors before populating.Colm Donelan
* When the tfLiteExecutor attempts to populate the input tensors it did not check whether the tensor was constant. This was causing segmentation faults. Signed-off-by: Colm Donelan <colm.donelan@arm.com> Change-Id: I80a4cc788de4ffe08afb2df9185d04fcb8b27c3a
2023-01-25IVGCVSW-7441 Fixing null pointers in ExecuteNetwork.Colm Donelan
* Check if BuildExecutor returns null in ExecuteNetwork. * Check if tflite BuildFromFile returns null in TfliteExecutor. Signed-off-by: Colm Donelan <colm.donelan@arm.com> Change-Id: I42b6e5f26dfd127dd16b6b322184900846317c41
2023-01-24IVGCVSW-7297 When creating multiple Executors only the lastMike Kelly
one works fine * All ArmNNExecutors now share a single IRuntime. * All armnn_delegates now share a single IRuntime. * Increased delegate major version. Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: I95cbdc32655ec0beb476dbb2d60f1a0209df8f04
2023-01-10Update --compare-output description in ExecuteNetwork parameters.Cathal Corbett
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com> Change-Id: Ic6bbbaa04aabaa5c3fd525acd5121f07d3392120
2023-01-06IVGCVSW-7031 Generate static execute networkRyan OShea
* Build ExecNet lib dependencies as object libs except libarmnn * Disable PIPE when building static ExecNet * Remove multiple definition from AsyncExecutionCallback * Disable DynamicBackend for ExecNet Static build * Disable inference tests for TfLiteParser and ONNX during static ExecNet * Remove Tensorflow Parser if condition * Add Disable thread macro to InferenceModel * Don't compile dynamic backend symbols in Runtime.cpp for Baremetal and Exenet Static Signed-off-by: Ryan OShea <ryan.oshea3@arm.com> Change-Id: If41c063eab5f05b3df0a6e064924a36a177f116a
2022-12-20IVGCVSW-7409 GPU backend options not being passed from the delegate.Colm Donelan
Two problems here: * First the Delegate was using the parameter options after the execution of std::move on it. * In ExecuteNetworkParams 3 GPU backend options were instead being set as optimizer options. Signed-off-by: Colm Donelan <colm.donelan@arm.com> Change-Id: I61c7fad8a5819a0a4aec0243899019a342c5cc5f
2022-12-13IVGCVSW-7365 Fix behaviour of --import-inputs-if-aligned in ExecuteNetworkMatthew Bentham
Move call to 'SetupInputAndOutputs' to after LoadedNetwork is available. Change-Id: I101e297d1d7b2517011d4ef3f1a4927566845474 Signed-off-by: Matthew Bentham <matthew.bentham@arm.com>
2022-11-16IVGCVSW-7214 Disable BF16-Turbo-Mode and remove conversion layersRyan OShea
- Remove Bf16ToFp32 Conversion Layer - Remove Fp32ToBf16 Conversion Layer - Remove B16 Conversion tests * Throw exception if m_ReduceFp32ToBf16 optimzer option is set to true * Provide comments to enable fast math in order to use bf16 * Update docs to inform users to enable fast math for bf16 Execute Network Changes * Require bf16_turbo_mode to also have fast_math_enabled set to true - Remove setting m_ReduceFp32ToBf16 optimizer option Signed-off-by: Ryan OShea <ryan.oshea3@arm.com> Change-Id: Ibaa6da9d29c96a1ce32ff5196b0847fde9f04a1c
2022-11-15IVGCVSW-7332 Fix Delegate Profiling in ExNet with multiple iterationsKevin May
Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: If837e4bec7940b53d18d0da32f3e736215dd2a03
2022-11-11IVGCVSW-7356 Bug Fix for Execute Network Delegate when input names not givenTeresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I2fd0f6aac6ffff695b17df7455f252f6013c0d43
2022-10-27IVGCVSW-7282 Issues in ExNet when iterations and number of inputs do not matchTeresa Charlin
* The intention is to keep the flexibility given by the ExNet before the refactor. * When iteration > inputFiles, we repeat the usage in order * When iteration < inputFiles, we just discard extra files. Signed-off-by: Adam Jalkemo <adam.jalkemo@arm.com> Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I2fbe69f8affe0e3a5cc86fc1748164967f0c2d64
2022-10-27Revert "IVGCVSW-7282 Issues in ExNet when iterations and number of inputs do ↵Teresa Charlin
not match" This reverts commit 6c95836e894f88c4bab6b22f974341f0dd2dddaa. Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I8be2147feb557a0849de5785fb63b464abc7dbb9
2022-10-25IVGCVSW-7282 Issues in ExNet when iterations and number of inputs do not matchCathal Corbett
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com> Change-Id: Ib30fc633a10b6ff8090b50314278fe5dc46fb250
2022-10-19MLCE-545 INT8 TFLite model execution abnormalKeith Davis
* Add functionality to print output tensors to file in tempdir * UnitTests Signed-off-by: Keith Davis <keith.davis@arm.com> Change-Id: Idfb4c186544187db1fecdfca11c662540f645439
2022-10-14IVGCVSW-7267 Make the AllowExpandedDims option workJim Flynn
Signed-off-by: Jim Flynn <jim.flynn@arm.com> Change-Id: I3573078206272c3a72a2b3acf8781ab458ea6c90
2022-10-13IVGCVSW-7288 ExecuteNetwork fix for multiple outputsAdam Jalkemo
* When a model with multiple outputs was used and output to file, e.g. with "-w ./boxes,./classes,./scores,./detection", the results where not saved in the correct files. * Applies only to the ArmNNExecutor. Change-Id: I2899322622a4c3fd1d0ddc75b100b81669417660
2022-10-13IVGCVSW-7283 Use stricter file extension check in CreateParserAdam Jalkemo
* I had issues when folder name contained "armnn" and a .tflite model was used, as the wrong parser was selected. * Now only the extension, and not the full string, is considered when selecting parser. Change-Id: If7964d2ce5535f7d25762d2a2d7e810bf1a1ed43
2022-10-11IVGCVSW-7222 Fix incorrect kernel measurements in profiling outputKevin May
* Some CL kernels are not run after the first inference and this breaks the profiler which is expecting a measurement for every kernel each run * Add a function HasKernelMeasurements() to ascertain if the Event is returning kernel measurements and if so insert 0.0 values for any missing kernel measurements. * Fix ExecuteNetwork to only print a json object after all inferences have completed Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: I99f2bb0db847f5a52ab4c5705b072155c6b6f333
2022-10-04MLCE-545 INT8 TFLite model execution abnormalKeith Davis
* Signed32 missing from CompareAndPrintOutput Signed-off-by: Keith Davis <keith.davis@arm.com> Change-Id: If3c93fb0d73c566ddcf439fceaa6d629029df18f
2022-09-27IVGCVSW-7235 Errors from LoadNetwork are being ignored in ArmNNExecutor.Colm Donelan
In ArmNNExecutor::ArmNNExecutor the call to m_Runtime->LoadNetwork was ignoring the Status result and continuing to execute with a failed network. In addition throwing an exception from the constructor resulted in a segmentation fault. * Modify IExecutor to allow the constructor to mark itself as failed. * Modify ArmNNExecutor to mark itself as failed when LoadNetwork returns an error. * Modify ExecuteNetwork to check the value of m_constructionFailed. Signed-off-by: Colm Donelan <colm.donelan@arm.com> Change-Id: Idf222cb2b66e1051875dc67046734f2b00b288d1
2022-08-05IVGCVSW-7179 Segfault running ssd_mobilenet_v2_int8 with ExNet and delegate.Teresa Charlin
* model was declared in the TfLiteExecutor constructor, instead of intializing m_Model * Working with this model that has 4 output we saw the the output names were not correct, this got fixed too Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I48f194ad4ba6af43d43e6eea336eb87ffee02dcc
2022-08-05IVGCVSW-7157 ExNet. interpreter chooses a different input type.Cathal Corbett
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com> Change-Id: If00d8dab2846c484a1969fb152cb9f8bd16e1b3e
2022-08-05Bug Fixes for refactor of the ExecuteNetwork.Teresa Charlin
* dot file to be generated when -v is given. It was only being generated when using the delegate as executor * output name read from m_Params.m_OutputNames instead of m_TfLiteInterpreter * typo: "delage" instead of "delegate" * QAsymmS8 templated as int8, instead of uint8 Change-Id: Ie13ae0f7e6395c0ebcb5ecda32e72082dee8aa6c Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: Iac97a23927ba42290ebeb3446bbd36da15045e07
2022-07-28Revert "Revert "IVGCVSW-6650 Refactor ExecuteNetwork""Teresa Charlin
This reverts commit 1a7f033768acb27da11503bd29abb468d2e77f9e. List of fixes to be able to add this code again: * "emplacing_back" the vector inputTensors into the vector m_InputTensorsVec outside the for loop * GetIOInfo() uses IOptimizedNetwork instead of INetwork, where the infered shapes are not saved * Add missing data type Signed32 to SetupInputsAndOutputs() * PrintOutputTensors() prints the actual output without dequantizing * Add profilingDetailsMethod as input in networkProperties in ArmNNExecutor constructor * Fix typos Change-Id: I91de166f87228282db3efa27431fe91458834442 Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: Ic6634d48892d11e5f146cdf285e1e333e93e9937 Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
2022-07-27IVGCVSW-7061: Use same sentence for Aynch execution in ExNetTeresa Charlin
* "Asynchronous Execution with std::launch:async..." * "Asynchronous Execution with Arm NN thread pool..." Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I93f6ae92fd5599d1042f0dfced7e90ef85e20463
2022-07-27IVGCVSW-7096 Harmonise macro ARMNN_TFLITE_DELEGATETeresa Charlin
* Remove ARMNN_TF_LITE_DELEGATE and DARMNN_TF_LITE_DELEGATE Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I3fc08da3fa0b733e6791c42f6bc59494f2bc26a6
2022-07-08Revert "IVGCVSW-6650 Refactor ExecuteNetwork"Nikhil Raj Arm
This reverts commit 615e06f54a4c4139e81e289991ba4084aa2f69d3. Reason for revert: <Breaking nightlies and tests> Change-Id: I06a4a0119463188a653bb749033f78514645bd0c
2022-07-08IVGCVSW-6650 Refactor ExecuteNetworkFinn Williams
* Remove InferenceModel * Add automatic IO type, shape and name configuration * Depreciate various redundant options * Add internal output comparison Signed-off-by: Finn Williams <finn.williams@arm.com> Change-Id: I2eca248bc91e1655a99ed94990efb8059f541fa9
2022-05-24IVGCVSW-6255 Investigate and fix running mobilebert with the TfLiteDelegate ↵Cathal Corbett
(CpuRef) * Fixed bug occuring in Ref Gather Workload. Signed-off-by: Cathal Corbett <cathal.corbett@arm.com> Change-Id: I3ee79f475fd9909bfbd4afb58f698439f26d6d65
2022-05-18IVGCVSW-6929 Support for models with implicit expandedMike Kelly
dimensions * Added allow-expanded-dims to TFLite parser and ArmNN delegate * If true ArmNN will disregard dimensions with a size of 1 when validating tensor shapes. Tensor sizes must still match. * This allows us to support models where tensors have expanded dimensions (i.e. extra dimensions with a size of 1). * Fixed bug in Network where it assumed that only the first option could be ShapeInferenceMethod. * Fixed bug where m_ShapeInferenceMethod was lost when copying or moving Graphs. * Changed Delegate to pass "infer-output-shape", "allow-expanded-dims" and other BackendOptions through to the Network during construction. Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: Ibe7c5ae6597796fc9164cb07bd372bd7f8f8cacf
2022-04-07IVGCVSW-6828 Add a 'reuse I/O buffers' iteration mode to ExecuteNetworkRyan OShea
* Add shorthand argument for no print * Add Execute network option to reuse buffers * Add new synchronous execute method to reuse buffers Signed-off-by: Ryan OShea <ryan.oshea3@arm.com> Change-Id: Ia7ee99b2ba9a21043c9575d7546bf25208357141
2022-03-01IVGCVSW-6704 Change the namespace from armnn::profiling to arm::pipeCathal Corbett
* Updated ABI version to 29 due to being the first ABI break in 22.05 !android-nn-driver:7226 Signed-off-by: Cathal Corbett <cathal.corbett@arm.com> Change-Id: I9c50007dcd5b5e792757e7bd1213606df5ffec36
2022-02-15IVGCVSW-6786 Add import if memory aligned option to ExecuteNetworkJim Flynn
Change-Id: Ib038e7b2616195a64715e3a7126da1368bbca1d3 Signed-off-by: Jim Flynn <jim.flynn@arm.com>
2022-02-14IVGCVSW-6708 Break Profiling Dependence on IRuntime ExternalProfilingOptionsJim Flynn
Change-Id: I30a46f3368bbbf33019eac4fa1245f6ff69deacd Signed-off-by: Jim Flynn <jim.flynn@arm.com>
2022-02-03IVGCVSW-6680 Delegate Segfaults on Execute NetworkRyan OShea
* Change to check for success instead of specific failure * Fix which map index is used when assigning outputs Signed-off-by: Ryan OShea <ryan.oshea3@arm.com> Change-Id: I13d8e989e35789ad3e2465d595905c5a5603ae0f
2022-01-24IVGCVSW-6733 Add missing qasymms8 output type to delegateFinn Williams
Signed-off-by: Finn Williams <finn.williams@arm.com> Change-Id: Ic5ebf7b80468b7751c234c43a90ec4cbf4c59ffe
2021-12-09IVGCVSW-6611 ExNet prints inference time twiceCathal Corbett
* Created individual IRuntime sharedptr in ExecuteNetwork main() each time MainImpl() is called. Prevents additional runtime being created when the delegate is used. Signed-off-by: Cathal Corbett <cathal.corbett@arm.com> Change-Id: Ia4b508fbf2bbd25467c6235fed2f05662a7aecc0
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
2021-11-30IVGCVSW-5611 TfLiteDelegate: Investigate and fix incorrect output from ↵Tamas Nyiri
Deep_speech models * Fixed output bindings in ExecuteNetwork when using delegate * Added extra comments (for my own comprehension) Change-Id: Ia1330903a2b724be7d637f6c5b6e4349e7d33e2e Signed-off-by: Tamas Nyiri <tamas.nyiri@arm.com>
2021-11-03Revert "IVGCVSW-6359 Added support for Float16 (Half) to Execute Network"David Monahan
This reverts commit 2d9956162dd002a41f7fb4fa6753195d33524c7f. Reason for revert: After some discussion, this does technically implement Float16 support for ExecuteNetwork, but not in a way which matches most use cases and is likely to cause issues in the future. Reverting for now. Change-Id: I4ce6de6879216e694631f5dc68e46fb793fae0a9
2021-11-01IVGCVSW-6359 Added support for Float16 (Half) to Execute NetworkDavid Monahan
* Allows the user to specify float16 as a datatype * Does not contain support for float16 on the TfLiteDelegate via ExecuteNetwork Signed-off-by: David Monahan <David.Monahan@arm.com> Change-Id: Icba56feedab32662e2cf671cc46ada899cf40c6c
2021-10-28IVGCVSW-6473 Add warnings to ExecuteNetwork on invalid output tensor type.Colm Donelan
* In ExecuteNetwork MainImpl compare the data types of outputs on the loaded model with those specified by the user through --output-type. Issue a warning if there is a mismatch. Signed-off-by: Colm Donelan <colm.donelan@arm.com> Change-Id: Ic5add9734dc239eddca0972a9e560e54abdb1093
2021-10-28IVGCVSW-6513: Compilation failure in armnn-mobilenet-quant in ML-ExamplesFrancis Murtagh
* Move TContainer to armnnUtils library Signed-off-by: Francis Murtagh <francis.murtagh@arm.com> Change-Id: I3c0f895d11b66f6ee224ac689a19d0477f990b98
2021-10-27IVGCVSW-5879 Fix problems with using internal profiling from delegate.Colm Donelan
* Pass through the value of m_EnableProfiling from Executenetwork to DelegateOptions. * If internal profiling is enabled print it out from inside the delegate. * Remove an unnecessary ProfilerImpl instance from WorkingMemhandle.hpp * Remove an unnecessary parameter from TfLiteDelegateMainImpl in ExecuteNetwork. Signed-off-by: Colm Donelan <colm.donelan@arm.com> Change-Id: Ia1d4b1eb3a05ca5b4d80cc39e138c7fac182d948
generated by cgit v1.2.1 (git 2.23.0) at 2024-07-17 00:19:33 +0000