Age | Commit message (Collapse) | Author |
|
Signed-off-by: John Mcloughlin <john.mcloughlin@arm.com>
Change-Id: Id4bdc31e3e6f18ccaef232c29a2d2825c915b21c
|
|
* 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
|
|
- 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
|
|
* Add functionality to print output tensors to file in tempdir
* UnitTests
Signed-off-by: Keith Davis <keith.davis@arm.com>
Change-Id: Idfb4c186544187db1fecdfca11c662540f645439
|
|
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>
|
|
This reverts commit 615e06f54a4c4139e81e289991ba4084aa2f69d3.
Reason for revert: <Breaking nightlies and tests>
Change-Id: I06a4a0119463188a653bb749033f78514645bd0c
|
|
* 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
|
|
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
|
|
Change-Id: Ib038e7b2616195a64715e3a7126da1368bbca1d3
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
|
|
* Enabled using same instance of SimpleLogger
* Removed some trailing new lines on some log messages
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I4b917c0ca5011afc9b39dad50715290ba15a1246
|
|
* Move TContainer to armnnUtils library
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: I3c0f895d11b66f6ee224ac689a19d0477f990b98
|
|
* Added a single definition of TContainer to include/armnn/Utils.hpp
* Change all files which contained their own identical definitions of TContainer to use the new one
Signed-off-by: David Monahan <David.Monahan@arm.com>
Change-Id: I63e633693a430bbbd6a29001cafa19742ef8309a
|
|
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: Ia7dbf0735619d406d6b4e34a71f14f20d92586e6
|
|
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
Change-Id: I04fb80c967bba4bb377de419bde618c1cbb80075
|
|
* Add functionality to only output network details in ExNet
Signed-off-by: Keith Davis <keith.davis@arm.com>
Change-Id: I0c45e67193f308ce7b86f1bb1a918a266fefba2e
|
|
* Add switch for network details during profiling
Signed-off-by: Keith Davis <keith.davis@arm.com>
Change-Id: I8bd49fd58f0e0255598106e9ab36806ee78391d6
|
|
* Pass m_shapeInferenceMethod to OptimizerOptions in ExecuteNetwork
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I90280fb7629092d3b66e8a3968ca9e35a0df854a
|
|
* Add new ProfilingDetails class to construct operator details string
* Add new macro which helps append layer details to ostream
* Add ProfilingEnabled to NetworkProperties so that profiling can be
realised when loading the network
* Add further optional info to WorkloadInfo specific to convolutions
* Generalise some JsonPrinter functions into JsonUtils for reusability
* Remove explicit enabling of profiling within InferenceModel as it is
done when loading network
* Add ProfilingDetails macros to ConvolutionWorkloads for validation
Signed-off-by: Keith Davis <keith.davis@arm.com>
Change-Id: Ie84bc7dc667e72e6bcb635544f9ead7af1765690
|
|
!android-nn-driver:5966
Change-Id: Ice0b4d2872bb0e09bfc0763034a206c3a8f24af4
Signed-off-by: Rob Hughes <robert.hughes@arm.com>
|
|
!android-nn-driver:5802
* Extract the threadpool from LoadedNetwork/Runtime
* Refactor the threadpool to be handle multiple networks
* Trim IAsyncExecutionCallback and add an InferenceId to AsyncExecutionCallback
* Add AsyncCallbackManager class
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I36aa2ad29c16bc10ee0706adfeb6b27f60012afb
|
|
profiling common
!android-nn-driver:5691
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ib71af0831e324ac6bd27b1a36f4a6ec1a703b14a
|
|
* 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
|
|
* 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>
|
|
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>
|
|
* 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
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ib00be204f549efa9aa5971ecf65c2dec4a10b10f
|
|
* 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
|
|
* 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
|
|
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I3f320499c379162f9d1b00cc8816bd144cd7eee4
|
|
* Added ability to set number of threads used in CpuAcc backend
* Enabled number-of-threads option in ExecuteNetwork
* Added TfLiteDelegate ModelOptions test
* Added unsigned int type to BackendOptions.hpp
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: Ia576d4f45cbe5df3654bc730bb5ebd5181d82b5a
|
|
* Added output log to capture time taken to load network into runtime.
* This time is cut down when loading a cached network.
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: I043c177f17d01df35fbe0752ec5d77e350749164
|
|
* Enable ability to save/load ClContext in ExecuteNetwork.
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: I58c61a53f6713853eb06520cc372ed47baf7f8c4
|
|
* Removed unused includes from InferenceModel.hpp.
* Replaced use of boost multi-array with vectors in YoloInferenceTest.
Signed-off-by: Colm Donelan <Colm.Donelan@arm.com>
Change-Id: Ieadf3471ed170b09859187c83616c8e249f94543
|
|
* refactor AddCommandLineOptions() functions to allow checking of required options
* add CxxoptsUtils.hpp file for convenience functions
!referencetests:268500
Signed-off-by: James Ward <james.ward@arm.com>
Change-Id: Ica954b210b2981b7cd10995f0d75fcb2a2f7b443
|
|
* replace boost::variant with mapbox::util::variant
* replace boost::apply_visitor with mapbox::util::apply_visitor
* replace boost::get with mapbox::util::get
Signed-off-by: James Ward <james.ward@arm.com>
Change-Id: I38460cabbcd5e56d4d61151bfe3dcb5681ce696e
|
|
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I4eb3e27837aea926593d49f9ccea07bab8388d5b
|
|
* Replaced with armnn/utility/NumericCast.hpp
* Removed combinations without float implementation in NumericCast.hpp
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: Ia4ec605f063cdb0071fff302ef48c610f9f9505e
|
|
* Replaced boost::format with fmt::format
Signed-off-by: James Ward <james.ward@arm.com>
Change-Id: Icf5a6508e7be3d31bc063643491fc5e0607f21fa
|
|
* Introduced infer-output-shape option to TfLiteParser in ExecuteNetwork app
!armnn:3591
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I30bd5e51ac2b6759169e22a44586fd97986f2402
|
|
* 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
|
|
* 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
|
|
* Removed split, classification, trim, string, join, contains
* Added StringUtils.hpp to replace the removed Boost String functionality
Signed-off-by: David Monahan <david.monahan@arm.com>
Change-Id: I8aa938dc3942cb65c512cccb2c069da66aa24668
|
|
* 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
|
|
Signed-off-by: David Monahan <david.monahan@arm.com>
Change-Id: I992379f03d1cfe3c019bb23786458d4f22df6b17
|
|
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I57ec47adf98680254fa481fb91d5a98dea8f032e
|
|
!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>
|
|
Change-Id: I593e2540bd870d70aabb2c959f4e63a899967269
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
* Moved to BackendRegistry.hpp include/armnn
* Updated makefiles and sources accordingly
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
Change-Id: I4d83abb581d523218a880c879fcf30c9611f7fd7
|
|
* 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
|
|
Signed-off-by: Matthew Jackson <matthew.jackson@arm.com>
Change-Id: Id7ab186ec607ff6e5ee6869c4ad562af4c40b97a
|