aboutsummaryrefslogtreecommitdiff
path: root/tests/ExecuteNetwork
AgeCommit message (Collapse)Author
2020-11-20IVGCVSW-5559 Add int8_t to tflite delegate on ExecuteNetworkFinn Williams
Signed-off-by: Finn Williams <Finn.Williams@arm.com> Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: I56afc73d48848bc40842692831c05316484757a4
2020-11-18IVGCVSW-5377 'Add ArmNN TfLite delegate to ExecuteNetwork'Sadik Armagan
* Assign correct input values for the model * Call the right Validate function for Mul and Sub operators * Return the correct data type for kTfLiteInt8 Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I6d23adf68d33d8be9a1fbf5d19dfe47939a6d3d6
2020-11-17IVGCVSW-5377 Add ArmNN TfLite delegate to ExecuteNetworkSadik Armagan
* Added package manger to turn internal calls to find_package into a no-op * Changed delegate cmake so it can now be built within armnn Change-Id: I2a7ecb9a3c1ca05474cd1dccd91498f6f6c0b32e Signed-off-by: Finn Williams <Finn.Williams@arm.com> Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
2020-11-17IVGCVSW-5465 ExecuteNetworkTestsDynamicBackends Bug FixKeith Davis
* When invalid backend specified an ARMNNLOG should be invoked to fail more gracefully Signed-off-by: Keith Davis <keith.davis@arm.com> Change-Id: Iec34fbc03dbeeb66836b0d5e1dd381d021a379b1
2020-11-11IVGCVSW-5507 ExecuteNetwork fixJan Eilers
* Allow multiple backends to be defined seperately like " --compute CpuAcc --compute CpuRef " Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: Ic2a827f6e3463a7413c98a7eefacef8864c1e87b
2020-10-27Bugfix: Allow use of dynamic backendId in execute networkFrancis Murtagh
* Stops execute network rejecting backendId based on BackendRegistry * Dynamically loaded backends arent visible yet as runtime isn't initialized Change-Id: I87adfd137b2225ab07f8c3e996db9565caf276eb Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
2020-10-20IVGCVSW-5284 Refactor ExecuteNetworkJan Eilers
* Removed boost program options and replaced it with cxxopts * Unified adding, parsing and validation of program options into the struct ProgramOptions * Program options are now parsed directly into ExecuteNetworkParams which can be passed directly to MainImpl * Split NetworkExecutionUtils into header and source * Removed RunTest * Removed RunCsvTest * Removed RunClTuning * Moved MainImpl back to ExecuteNetwork.cpp * Added additional util functions The functionality of ExecuteNetwork remains the same. Only cl tuning runs need to be started separately and there is no short option for fp16-turbo-mode because -h is reserved in cxxopts to print help messages Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: Ib9689375c81e1a184c17bb3ea66c3550430bbe09
2020-10-12IVGCVSW-5335 Documentation for fast_mathMike Kelly
* Changed documentation for fast_math to add warning about possibly reduction in precision. Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: If954471efc6aef702e8490585571815d9e19b3fc
2020-09-22IVGCVSW-5318 'Create a Neon/CL Workload Unit Test fast_math option enabled'Sadik Armagan
* Unit test implemented to make sure it returns WINOGRAD * Updated the enable-fast-math option in ExecuteNetwork to be consistent Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: Id64f114ae47966def69a9eef0770a4251ee56a41
2020-09-15IVGCVSW-5317 'Add enable_fast_math Option to ExecuteNetwork'Sadik Armagan
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I4eb3e27837aea926593d49f9ccea07bab8388d5b
2020-07-29IVGCVSW-4980 Introduce InferAndValidate option to ExecuteNetwork for parsersSadik Armagan
* Introduced infer-output-shape option to TfLiteParser in ExecuteNetwork app !armnn:3591 Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I30bd5e51ac2b6759169e22a44586fd97986f2402
2020-06-30IVGCVSW-4487 Remove boost::filesystemFrancis Murtagh
* Replace filesystem::path * Replace filesystem::exists * Replace filesystem::is_directory * Replace filesystem::directory_iterator * Replace filesystem::filesystem_error exception * Replace filesystem::temp_directory_path * Replace filesystem::unique path * Replace filesystem::ofstream with std::ofstream * Replace filesystem::remove * Replace filesystem::is_regular_file * Replace boost::optional with armnn::Optional in touched files * Remove some superfluous includes * Update build guides, GlobalConfig.cmake and CMakeLists.txt * Remove redundant armnnUtils::Filesystem::Remove function. * Remove redundant armnnUtils::Filesystem::GetFileSize function. Temporarily adding back Boost::filesystem to enable Boost::dll. Signed-off-by: Francis Murtagh <francis.murtagh@arm.com> Signed-off-by: Colm Donelan <Colm.Donelan@arm.com> Change-Id: Ifa46d4a0097d2612ddacd8e9736c0b36e365fb11
2020-06-03remove BOM from filesLaurent Carlier
Change-Id: Ia4b4bb3be0ed6e933c77d58f8e9879b1370e9537 Signed-off-by: Laurent Carlier <laurent.carlier@arm.com>
2020-05-22Adding more performance metricsalered01
* Implemented CLTuning flow for ExecuteNetwork tests * Added --tuning-path to specify tuning file to use/create * Added --tuning-level to specify tuning level to use as well as enable extra tuning run to generate the tuning file * Fixed issue where TuningLevel was being parsed incorrectly * Added measurements for initialization, network parsing, network optimization, tuning, and shutdown * Added flag to control number of iterations inference is run for Signed-off-by: alered01 <Alex.Redshaw@arm.com> Change-Id: Ic739ff26e136e32aff9f0995217c1c3207008ca4
2020-05-13IVGCVSW-4825 Set default value for --file-format argument in ExecuteNetworkFinn Williams
Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: I834ef1ec7c2c7b5ece1c6d1cf3cfe5d856cde349
2020-04-27IVGCVSW-4722 Add missing m_TimelineEnabled bool to ↵Finn Williams
ConnectionAcknowledgedCommandHandler * Added timeline bool to ConnectionAcknowledgedCommandHandler * Added option to enable timeline profiling in ExecuteNetwork * Added CommandHandler stub to allow gatordMock to ignore packets Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: I314f9411e0079cba8f103d3b8a89f2bf38bb21ab
2020-04-06IVGCVSW-4485 Remove Boost assertNarumol Prangnawarat
* Change boost assert to armnn assert * Change include file to armnn assert * Fix ARMNN_ASSERT_MSG issue with multiple conditions * Change BOOST_ASSERT to BOOST_TEST where appropriate * Remove unused include statements Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: I5d0fa3a37b7c1c921216de68f0073aa34702c9ff
2020-03-24IVGCVSW-4521 Add bf16-turbo-mode option to ExecuteNetworkNarumol Prangnawarat
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: I57ec47adf98680254fa481fb91d5a98dea8f032e
2020-03-20IVGCVSW-4588 Remove short form of option file-formatNikhil Raj
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: I90bbe9406d81320289d9878700d738f6b33d8a94
2020-03-19MLECO-755: ArmNN: Add file format external profiling optionIsabella Gottardi
* Added new m_FileFormat variable in ExternalProfilingOptions * Added new profiling option to ExecuteNetwork * Added check for file format in ProfilingConnectionFactory * Added test in profiling tests Change-Id: I0e9cb8ecac919dc0ed03dcf77324a65621f07ae7 Signed-off-by: Isabella Gottardi <isabella.gottardi@arm.com>
2020-02-20COMPMID-3062: Add ExecuteNetwork option to explicitly dequantize outputGeorgios Pinitas
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Change-Id: Ic7abe5dad700fbdc1b7cbab6936b52554f0a0360
2019-12-05Replace boost logging with simple loggerDerek Lamberti
!referencetests:214319 * Reduces arm nn binary size ~15% * Also fixed test logging black hole issues Change-Id: Iba27db304d9a8088fa46aeb0b52225d93bb56bc8 Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
2019-12-02IVGCVSW-4206 Optionally parse unsupported ops in ExecuteNetworkDerek Lamberti
Change-Id: I593e2540bd870d70aabb2c959f4e63a899967269 Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
2019-10-25IVGCVSW-4008 Add profiling mode to ExecuteNetworkAron Virginas-Tar
* Removed the requirement for specifying a data file for each input tensor * Added the possibility to generate dummy tensor data (filled with 0s) if no data files are specified by the user * Warn the user when they request to save the output to a file, but the input was generate, therefore rendering the output useless Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I8baed116dcd99fe380e419db322dc7e04ab1c653
2019-10-22IVGCVSW-4021 Fixing failure in the ExecuteNetworkDynamicBackends testNikhil Raj
Change-Id: I24ecd8ccf3e3c1586abc906f6ee9bdfd652e5c39 Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
2019-10-17IVGCVSW-3721 Add support for startup sequence (Mock Gatord service).Colm Donelan
* Updated ExecuteNetwork to propagate a configured Runtime down to RunTest. * Fixed the creation of PeriodicCounterCaptureCommandHandler to match other handlers. * Moved around some printouts to make the MockGatorD output more useful. * Added details to the exception handling for problems in the GatordMockService receive thread. * Mockutils::ConstructHeader is only used in GatordMockTests. Moved it in there and deleted MockUtils.hpp * Refactored SendPeriodicCounterSelectionList to use ProfilingUtils. * Added PeriodicCounterSelectionResponseHandler to received packet echoed back. Signed-off-by: Colm Donelan <Colm.Donelan@arm.com> Change-Id: I4accdbf6cf5dd3f7dcc12b210b8360b4a5e4e277
2019-10-08IVGCVSW-3669 Fix bug parsing multiple InputShapes in ExecuteNetworkFrancis Murtagh
* Change shape separator from semicolon, a command separator, to colon. * Update ExecuteNetwork --help prompts. Change-Id: I6c6d18007cd219482d8187d69962944b833e302e Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
2019-10-04IVGCVSW-3948 Adds External Profiling cmdline to ExecuteNetworkJim Flynn
Change-Id: If172bcb64e8202abbde4b8a6cee14f672bc259cd Signed-off-by: Jim Flynn <jim.flynn@arm.com>
2019-09-06IVGCVSW-3816 Make compute option required in ExecuteNetworkMatthew Jackson
Signed-off-by: Matthew Jackson <matthew.jackson@arm.com> Change-Id: If13b731d95c79e3e296d7dfc6c1ac94bf3a93ff3
2019-09-04IVGCVBENCH-1337 Added additional layer parameters to dot file and -v optionAndre Ghattas
* Generic layer parameters now show up in dot file * Convolution layer parameters have also been added to dot file * ExecucteNetwork has an additional -v flag which generated dot file if there Change-Id: I210bb19b45384eb3639b7e488c7a89049fa6f18d Signed-off-by: Andre Ghattas <andre.ghattas@arm.com> Signed-off-by: Szilard Papp <szilard.papp@arm.com>
2019-09-02IVGCVSW-2945 ExecuteNetwork should have an option to save the output to a fileSadik Armagan
* Added "output-tensor-files,w" option to save output tensors to a file Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: Ida457177c5cbd7dca228772405fd505d03b61bf9
2019-08-28IVGCVSW-3675 Add ExecuteNetwork option to print intermediate layersMatthew Jackson
Signed-off-by: Matthew Jackson <matthew.jackson@arm.com> Change-Id: Id7ab186ec607ff6e5ee6869c4ad562af4c40b97a
2019-08-23IVGCVSW-3547 Use ExecuteNetwork to run a dynamic backend end to end testMatteo Martincigh
* Added path override for dynamic backend loading * Do not default to CpuRef, as there could be dynamic backends loaded at runtime * Do not check right away whether the backends are correct, as more of them can be loaded at runtime as dynamic backends Change-Id: If23f79aa1480b8dfce57e49b1746c23b6b9e6f82 Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
2019-06-26IVGCVSW-3193 Allow ExecuteNetwork to have qasymm8 input typeNarumol Prangnawarat
and add option to quantize float inputs to qasymm8 Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: I54b13b8b53c31c05658fe9c310ca5a66df759aa5
2019-06-19IVGCVSW-3299 Add Uint8 Support to Model Accuracy CheckerFrancis Murtagh
* Seperate ExecuteNetwork main function into standalone application * Include NetworkExecutionUtils header and remove duplicate functions * Add uint8 and int32 support to ModelAccuracyChecker Change-Id: I5fb4bc147232f8388f37eea7db5130b04fd215d1 Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
2019-05-14IVGCVSW-3001 Dequantize the output prior to printingDerek Lamberti
Change-Id: Ibd5fb4ad102aec1f71ab99402a3e3a08b04b926b Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
2019-04-15IVGCVSW-2928 Fix issue with GPU profilingMatthew Bentham
Correctly enable GPU profiling when test profiling is enabled. Remove extra copy of the profiling-enabled flag from InferenceModel::Params and correctly pass around the copy that is in InferenceTestOptions. !referencetests:180329 Change-Id: I0daa1bab2e7068fc479bf417a553183b1d922166 Signed-off-by: Matthew Bentham <matthew.bentham@arm.com>
2019-04-11IVGCVSW-2543 Add timing for ExecuteNetwork inferenceJames Conroy
* Adds a new command line option 'threshold-time' to ExecuteNetwork, the maximum allowed time for inference in EnqueueWorkload. * ExecuteNetwork now outputs inference time elapsed and (if supplied) threshold time. * If actual elapsed inference time is greater than supplied threshold time, fail the test. Change-Id: If441b49a29cf5450687c07500c9046a80ece56fc Signed-off-by: James Conroy <james.conroy@arm.com>
2019-04-03IVGCVSW-2802 Ability to run FP16 turbo mode through ExecuteNetworkRuomei Yan
Change-Id: I679883234d78b95d1e01ed5602c5cab296b0c6bf Signed-off-by: Ruomei Yan <ruomei.yan@arm.com>
2019-02-26IVGCVSW-2629 Adding support for uint8 in ExecuteNetwork to fix issues with ↵Éanna Ó Catháin
output tensor being all zero Change-Id: I4da1ffd684672fff0853fb053c3340d06a3bc165 Signed-off-by: Éanna Ó Catháin <eanna.ocathain@arm.com>
2019-02-20IVGSVSW-2736 Rename DeserializeParser => Deserializer & fix namespacesDerek Lamberti
Change-Id: I4166c0bbb5ba7f8b8884e71134c21f43d1fc27b0 Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
2019-02-12IVGCVSW-2663 Enable ExecuteNetwork to load ArmNN filesAron Virginas-Tar
Change-Id: I1a61a1da2258bd07b39da6063d22a5bd22c1884d Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
2019-02-11IVGCVSW-2529 DeepSpeech v1 testFerran Balaguer
Change-Id: Ieb99ac1aa347cee4b28b831753855c4614220648
2019-02-01IVGCVSW-2604 Fix bug that made it impossible to execute inference tests on ↵Aron Virginas-Tar
certain backends * Read compute devices from the CL as strings and convert them into BackendId objects afterwards Change-Id: Icded1c572778f5a213644e3052ff6dfe7022128b Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
2019-01-31IVGCVSW-2601 Fix for ExecuteNetwork output data printing bugAron Virginas-Tar
Change-Id: I7e8d377cdbddf0176ae05d8b6b2fd03c6f614168 Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
2019-01-31IVGCVSW-2564 Fix output buffer initialization bug in ExecuteNetworkAron Virginas-Tar
Change-Id: I69eac52c9c944a5d209c5c7432c1b7f46e64f05b Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
2019-01-30IVGCVSW-2564 Add support for multiple input and output bindings in ↵Aron Virginas-Tar
InferenceModel Change-Id: I64d724367d42dca4b768b6c6e42acda714985950
2019-01-22IVGCVSW-2535 Fix crash in ExecuteNetwork when no compute device is specifiedAron Virginas-Tar
Change-Id: If8d6516286557a6381561805cd53b5659b38f6a6
2019-01-15IVGCVSW-2454 Merge together the pluggable backends work (was in aMatteo Martincigh
separate branch) and master * Brings in all the changes done for the pluggable backends * Added sub-graph support and tests * Added precompiled layer support and tests * Moved BackendSettings to a separate file * Removed the backend-specific code * Ported DebugLayer and associated functionality * Included fixes to make those changes work with master Change-Id: Id7028fa7917527b844628d5aff5732e3d94c0488
2018-10-29Fixed backend id argument parsing in ExecuteNetworkMatteo Martincigh
Change-Id: I99498a633d75a2b4bdcd059627b07beaa9984890
generated by cgit v1.2.1 (git 2.23.0) at 2024-06-17 16:44:09 +0000