Age | Commit message (Collapse) | Author |
|
* Added ITimelineDecoder.h C interface
* Added an example implementation of ITimelineDecoder.h
* Added command handlers for the timeline directory and objects
* Added tests for the decoder implementation
* Changed ReadSwTraceMessage to take a const unsigned char*
so it can be used by the directory command handler
* Fixed some bugs in ProfilingUtils.cpp and related tests
Change-Id: If06faf1fe0274a8f022f194a6d3527f5ce5374c6
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
|
|
* Add FileOnlyProfilingConnection Decorator
* Fix bug where Conn Ack not automatically sent back
* Modify GatordMock to use the Counter Directory class.
* Promote DirectoryCaptureCommandHandler from GatordMock into ArmNN.
* Remove MockUtils as it's contents were moved or deleted.
* Rewrite GatordMockTests to use Counter Directory class.
* Flush streams in ProfilingConnectionDumpToFileDecorator::Close.
Signed-off-by: Keith Davis <keith.davis@arm.com>
Signed-off-by: Colm Donelan <Colm.Donelan@arm.com>
Change-Id: I77b2aedece24150dd31691b577f3b5d81b2e226f
|
|
* Refactoring of some of the public API headers
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
Change-Id: I9006fe49945b10a6b83908b05aa4a6556639b491
|
|
* Moved to BackendRegistry.hpp include/armnn
* Updated makefiles and sources accordingly
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
Change-Id: I4d83abb581d523218a880c879fcf30c9611f7fd7
|
|
breaking some of the nightly builds
* The TensorPrinter must be called regardless of the value of
the output tensor files, it will automatically handle an empty
file path by only printing the results to the console
* Code refactoring
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
Change-Id: I548ec7cf6d51badf78643c9a6c1c56ea9200142b
|
|
* Moved QuntizeHelper.hpp to armnnUtils
* Reordered parameters for QuantizedVector and added default
values for qScale and qOffset to make life easier when
using the function for non-quantized types such as Float16
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I28c263dfa425f1316feccb4116839a84f5d568e5
|
|
* 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: Jammy Zhou <jammy.zhou@gmail.com>
Change-Id: I12562c4a9671cd43884e7c0c023ca463a99c3aa2
|
|
Change-Id: I24ecd8ccf3e3c1586abc906f6ee9bdfd652e5c39
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
|
|
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: If388e60434eae39d82b639d2275680679963624c
|
|
Fixing logic error in PeriodicCounterCaptureCommandHandler. Default
quiet operation should be false and the unit tests should set it to
true.
Signed-off-by: Colm Donelan <Colm.Donelan@arm.com>
Change-Id: Icabf30819985811e42168a98909b44a6c5f5d4df
|
|
Change-Id: Ief9373871438df4e1d353bbc545a3ee4f25c1fb0
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
|
|
Change-Id: I0bb0bf77da2bcd7f4746078c4ccee9acc98638a7
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
|
|
* 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
|
|
* Using proper include directives with include paths
* The relative paths used were causing trouble when building
on other CI systems
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
Change-Id: I897a80d1f56fbdbc3c714a50a0598210d8f0a03c
|
|
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: If481bc80fbad307f14d89beac9dc0d8fc575d788
|
|
* Receive and process the stream metadata from the client.
* Send the connection ack packet.
* Wait in a receiving thread and print the packets.
* GatordMockTest and Impl for PeriodicCounterCapture CommandHandler
* CaptureData class to retain packet data
* MockUtils
* Update SocketProfilingConnection to fix non blocking receipt of packets.
* Restructure directory layout following review comments.
* Extract the mock service into a static library in the cmake files.
Signed-off-by: Colm Donelan <Colm.Donelan@arm.com>
Signed-off-by: Keith Davis <keith.davis@arm.com>
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Signed-off-by: Kevin May <kevin.may@arm.com>
Change-Id: I33c1c9f93976708c9315f71290d42cff53b8c075
|
|
* 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>
|
|
Change-Id: If172bcb64e8202abbde4b8a6cee14f672bc259cd
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
|
|
* Variable-length array replaced with std::vector
* "and" replaced with "&&" (OK, this one is standard but MSVC doesn't
like it and it's inconsistent with the rest of the codebase)
* Replace u_int8_t with uint8_t
Change-Id: I7b968a2cfa85a5492a2a547364464c594efb067b
Signed-off-by: Rob Hughes <robert.hughes@arm.com>
|
|
* Add a CLI paramter to the Gatord mock client to specify a namespace.
* Open a listening socket on that namespace.
* Wait for one connection on the socket.
Signed-off-by: Colm Donelan <Colm.Donelan@arm.com>
Change-Id: Ic85b4defd5ad2010bb255472c030a91a23cec1d9
|
|
Introduce a new test utility that simulates the Gatord service.
This will be used to test the external profiling features.
Change-Id: Ib7c75c1302650e140945cd66d272c23af3aac760
Signed-off-by: Colm Donelan <Colm.Donelan@arm.com>
|
|
Signed-off-by: Matthew Jackson <matthew.jackson@arm.com>
Change-Id: If13b731d95c79e3e296d7dfc6c1ac94bf3a93ff3
|
|
* 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>
|
|
* 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
|
|
* If the number of the declared output types does not match
the number of outputs, throw an error (just like we do for
the inputs)
Change-Id: I1cb873bf443a31ecdbc11195462e9614ae3a6637
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
|
|
Signed-off-by: Matthew Jackson <matthew.jackson@arm.com>
Change-Id: Id7ab186ec607ff6e5ee6869c4ad562af4c40b97a
|
|
* 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>
|
|
Signed-off-by: FinnWilliamsArm <Finn.Williams@arm.com>
Change-Id: Ibf2b5ce5e50d72d661a7c720c1f3bb1c0d811700
|
|
Signed-off-by: SiCong Li <sicong.li@arm.com>
Change-Id: Id753fa1ea7a0aabc95b319cb78492f4220b701a4
|
|
* Replace u_int32_t with uint32_t
* Replace size_t with uint32_t for initializer list of TensorInfo
* Replace variable size arrays with std::vector
* Replace reference to local variable during its initialisation
Change-Id: I298b3995f1525f90a1ab2416d7e270315698fae3
|
|
* Fix the issue that uint8_t image tensors are written out as
characters.
* Add doxygen comments.
Signed-off-by: SiCong Li <sicong.li@arm.com>
Change-Id: Ic5b3af489f405abcc1ed1e7dd76f56c5ae7ffbf4
|
|
* Fix ImageTensorGenerator command line options
* Update ModelAccuracyTool README
* Update ImageTensorGenerator README
Signed-off-by: SiCong Li <sicong.li@arm.com>
Change-Id: I19e573f2b4aa0d7ecab63dc3886a66aa9d8724bc
|
|
* Evaluate model accuracy using category names instead of numerical
labels.
* Add blacklist support
* Add range selection support
Signed-off-by: SiCong Li <sicong.li@arm.com>
Change-Id: I7b1d2d298cfcaa56a27a028147169404b73580bb
|
|
Signed-off-by: Kevin May <kevin.may@arm.com>
Change-Id: Ic4177278bb8fb9e6e7e3c03ff8f49bfa99f5efdd
|
|
We can obtain the output tensor shape from the model provided by
the user.
Signed-off-by: SiCong Li <sicong.li@arm.com>
Change-Id: I5074734315174c1b5dc8eea1eff18a4a1c566f2a
|
|
* Refactor ImageTensorGenerator into a header so that it can be used
inside ModelAccuracyTool. ModelAccuracyTool now can accept image files
instead of tensor text files as input. ImageTensorGenerator remains a
standalone tool for converting images into tensors text files.
* Inside the ImageTensorGenerator, use the existing image preprocessing
method InferenceTestImage::Resize which has the correct image normalization
techniques and other resize utilities.
Change-Id: Ia662fed4752fb81c5cfa6d15967c6aae4aaf1155
Signed-off-by: SiCong Li <sicong.li@arm.com>
|
|
and add option to quantize float inputs to qasymm8
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I54b13b8b53c31c05658fe9c310ca5a66df759aa5
|
|
Convolution2d and DepthwiseConvolution2d to use Encoders and Decoders
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: Ic87b8ce6f68343983f3c825902425516cbb23b06
|
|
* 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>
|
|
* Validation files need to be changed due to image pre-processor fix:
IVGCVSW-3129
* Updated TfLiteVGG16Quantized-Armnn Validation.txt
* Updated TfLiteMobileNetQuantizedSoftmax Validation.txt
Change-Id: I801978cc9d658542e5b5d966347de3381191ad66
Signed-off-by: FinnWilliamsArm <Finn.Williams@arm.com>
|
|
* Changed expected predictions for TfLiteVGG16Quantized-Armnn.cpp
* Changed expected predictions for TfLiteMobileNetQuantizedSoftmax-Armnn
Change-Id: I3fe0bd3f6e44655b14b10887bc40fb0df31f81c8
Signed-off-by: FinnWilliamsArm <Finn.Williams@arm.com>
|
|
* Resized images for quantized models are now statically cast to uint8
instead of quantized
* Removed optional quantization parameters from ImagePreprocessor
constructor
* Changed mean and scale for TFLite models
Signed-off-by: FinnWilliamsArm <Finn.Williams@arm.com>
Change-Id: Id5ffdf77f3614d10c417e769bd8ffc4a4c07308b
|
|
* Added Readme file for ArmnnQuantizer
* Added section about ArmnnQuantizer in armnn Readme file
* Updated ModelAccuracyTool Readme file with default values for --compute
Signed-off-by: Nina Drozd <nina.drozd@arm.com>
Change-Id: I5fcead522b70086dcf63dfc6c77910a7d33d83f0
|
|
Change-Id: I92a1e043d60fa2fe3414dc9339ef36204aca42e2
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
Change-Id: Ibd5fb4ad102aec1f71ab99402a3e3a08b04b926b
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
Signed-off-by: Conor Kennedy <conor.kennedy@arm.com>
Change-Id: I1e128982ba0e1c99ee4532276f679dda37095201
|
|
Signed-off-by: Conor Kennedy <conor.kennedy@arm.com>
Change-Id: I071225a812e6f85b6abe83172be71913186523f4
|
|
Change-Id: I4ac325e45f2236b8e0757d21046f117024ce3979
Signed-off-by: Éanna Ó Catháin <eanna.ocathain@arm.com>
|
|
Change-Id: I4352a645badde788b9e33b3675a9cc9c0fc3dc33
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
|