Age | Commit message (Collapse) | Author |
|
* 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>
|
|
Signed-off-by: Colm Donelan <Colm.Donelan@arm.com>
Change-Id: Ic0a2e62e3808caf89ee429ec184d947a04340248
|
|
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>
|
|
* 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
|
|
* 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: Ida37d3ee3a1af0c75aa905199bd861726c646846
|
|
Signed-off-by: Kevin May <kevin.may@arm.com>
Change-Id: I8a29df03afdd6f1cc8413b219e179272cd2d51cf
|
|
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
|
|
* Enable GPU profiling on ExecuteNetwork
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I57bb4eeb45674e5218fce7e67b9bddf16ba0894d
|
|
abs is int type, use fabsf instead for float type
Signed-off-by: Keith Mok <ek9852@gmail.com>
Change-Id: I157d471da25d66cbe39fa9809ff9ee536d4e95a1
|
|
Instead of using the predefined backend ids,
we should just pass the backend string directly to the optimator,
otherwise we cannot use vendor specific backends or GpuAcc
Signed-off-by: Keith Mok <ek9852@gmail.com>
Change-Id: Ic52c81d48364a19f0fcc59bc3c975cf3bd740e21
|
|
* 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
|
|
The input tensor data pointer was passed incorrectly
Signed-off-by: Keith Mok <ek9852@gmail.com>
Change-Id: I03f872c57ec588fde0f7d444c80b38823ea4f9b4
|
|
inference time.
Usage: armnn_tfl_benchmark -m <model .tflite>
-m --model_file <.tflite file path>: .tflite model to be executed
-b --backend <device>: preferred backend device to run
layers on by default. Possible
choices: CpuAcc, CpuRef
-l --loops <int>: provide the number of time the
inference will be executed
(by default nb_loops=1)
Signed-off-by: Vincent ABRIOU <vincent.abriou@st.com>
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
Change-Id: Ia26fafd4f382f0ad03856436dcae6e71b5abbd26
|
|
* Allow passing multiple preferred backends as comma separated list
e.g. "-c CpuAcc,CpuRef" or by repeating the option "-c CpuAcc -c CpuRef"
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: I8e304d26c2890b99d5ec4c1af6c372458fa70051
|
|
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: If716f5f4e9b5433586b8a939d326830482da2f74
|
|
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
|
|
Signed-off-by: Kevin May <kevin.may@arm.com>
Change-Id: I52448938735b2aa678c47e0f3061c87fa0c693b1
|
|
* 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
|
|
* Report the error thrown
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: If5e5160f43c11a284b919d76b04d9c4d53e9c56c
|
|
* Added ModelOptions documentation to CLBackendModelContext
* Improved options descriptions in ExecuteNetworkProgramOptions.cpp
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: I14f0c8bb4f299809b89f49c616b691e2f7956d5b
|
|
* Enable ability to save/load ClContext in ExecuteNetwork.
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: I58c61a53f6713853eb06520cc372ed47baf7f8c4
|
|
Change-Id: Iecd8d9b333fa4456d081b4787c1a5b5d0b4a2b79
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
* Fixed issue when running certain models with 2D shape tensor.
* Falls back to inbuilt options if encountered.
* Fixed ExecuteNetwork so that error messages are logged if NULL.
* Updated TfLiteDelegate docs to include Logical Operators.
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Signed-off-by: David Monahan <david.monahan@arm.com>
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I5dbaf30351f7fc86e6178a0caf46c152812088d3
|
|
* Added support for building the delegate with an external armnn path
* Replaced potentially troublesome package manager
* Explicitly set the privacy levels of delegate libraries
* Fixed some error handling in ExecuteNetwork
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I2a7abc099796012cbb043c5b319f81778c9f3b56
|
|
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Signed-off-by: Kevin May <kevin.may@arm.com>
Change-Id: I56afc73d48848bc40842692831c05316484757a4
|
|
* 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
|
|
* 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>
|
|
* 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
|
|
* Allow multiple backends to be defined seperately like
" --compute CpuAcc --compute CpuRef "
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: Ic2a827f6e3463a7413c98a7eefacef8864c1e87b
|
|
* Fmt didn't get installed properly. Each component of an interface
library needs to be installed separately.
* Changed fmt to be a static library
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: Ic69bc9536ee01eed7b434b1ff53150581ba60e00
|
|
* 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
|
|
* Remove armnnUtils/CsvReader and usage
* Remove armnn/CsvReaderTest and usage
* Replace functionality in QuantizationDataSet.cpp
Signed-off-by: James Ward <james.ward@arm.com>
Change-Id: I7213904482afa93ae6d607aa5e69117c8c34ea81
|
|
* Remove all but Boost_UNIT_TEST_FRAMEWORK_LIBRARY from
ArmNN Cmake files.
* Remove references to boost::fpc from old test applications.
Signed-off-by: Colm Donelan <Colm.Donelan@arm.com>
Change-Id: Ibb1261dee4b971d1788d2805528aa800a8b883ce
|
|
* 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>
|
|
* 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
|
|
* 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
|
|
* 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
|
|
* 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
|
|
* Optional cmd option to dump optimized model to dot
* Optional cmd option to specify dynamic backends path
* input is now optional and must exist if given
* comparison files now optional and must exist if given
Change-Id: I1499c9eb715be3cacdba2c227e1a93dd997f355d
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
Signed-off-by: James Ward <james.ward@arm.com>
Change-Id: Ia4ff69f2c8dd538ad7845053dc7a690f434c381c
|
|
* Required update to cxxopts v3.0 for unrecognised options to work.
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: If1803731474e42580d663c802a1f3ff240fadffe
|
|
* Fixed two code errors which were causing compiler issues.
* Added support for multiple input and output tensors.
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: I298e4bf52a0b41349adab60295e0f22da3cc057b
|
|
* Removed from ModelAccuracyTool-Armnn and ImageCSVFileGenerator
* Fixed formatting in ImageCSVFileGenerator
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: I09dfca27813582cc48f46d0507680368ed823a9c
|
|
* Floating point casts now use armnn::numeric_cast.
* Also removed remaining header imports.
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: I2d37847d67f164fc0a0ae17f34d49ff3d2210c30
|
|
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: I1b2ba4fcaebbafb70693b83b40b79db0071b4522
|
|
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: I9d43e347021634022a875fc4526baa438c467df0
|