Age | Commit message (Collapse) | Author |
|
* Implement the "-C" command line option of executenetwork.
* Add a FileComparisonExecutorFile which will read tensors from
a previously written text file and compare them to the execution
output.
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: I8380fd263028af13d65a67fb6afd89626d1b07b8
|
|
* conversion from ‘double’ to ‘float’ changes value
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: Iebcc8adea54590fb6153db503e1dfccb082c9bd3
|
|
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
|
|
This tool forces explicit includes of all dependencies and
highlights unused dependencies.
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: I92e449245246452a0227cbd13f9c082e2088bf8c
|
|
Change-Id: I594ded82493e9cc48cafa6f00d63769fefba5afe
|
|
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
|
|
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
|
|
* 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
|
|
* 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: Jan Eilers <jan.eilers@arm.com>
Change-Id: I01aa6ea4b21ad4504d6ae04850a2236588e5ddd3
|
|
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: I10fb010ee8d3f813d2264cefb526f352e30d7046
|
|
* Added support for qasymms8 (int8) to ImageTensorGenerator
* Added qasymmu8 as alias for qasymm8 in ImageTensorGenerator
* Added support for qasymms8 (int8) to ExecuteNetwork
* Added qasymmu8 as alias for qasymm8 in ExecuteNetwork
* Set tflite to be the default model format in ImageTensorGenerator as
it's the only supported model format.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: Ieda7b78e668ea390e3565cd65a41fe0a9c8a5b83
|
|
!android-nn-driver:5966
Change-Id: Ice0b4d2872bb0e09bfc0763034a206c3a8f24af4
Signed-off-by: Rob Hughes <robert.hughes@arm.com>
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ida37d3ee3a1af0c75aa905199bd861726c646846
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ib00be204f549efa9aa5971ecf65c2dec4a10b10f
|
|
* 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>
Signed-off-by: Kevin May <kevin.may@arm.com>
Change-Id: I56afc73d48848bc40842692831c05316484757a4
|
|
* 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
|
|
* 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
|
|
* 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
|
|
* Introduced infer-output-shape option to TfLiteParser in ExecuteNetwork app
!armnn:3591
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I30bd5e51ac2b6759169e22a44586fd97986f2402
|
|
Change-Id: Ia4b4bb3be0ed6e933c77d58f8e9879b1370e9537
Signed-off-by: Laurent Carlier <laurent.carlier@arm.com>
|
|
* Remove redundant asserts for unsigned ints being positive
* Remove unneeded include of lightweight_test.hpp header
* Remove unused exception variable names
* Replace hardcoded 0.0f with T() for some template functions
* Add a few static_casts
Change-Id: I290b0433cf995f6d0199422eaa10f816e5fd8eb9
Signed-off-by: Robert Hughes <robert.hughes@arm.com>
|
|
Change-Id: I4b4d8ae419dfb8470e8937e75cd3bab85f03b935
Signed-off-by: Pavel Macenauer <pavel.macenauer@nxp.com>
|
|
* 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: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I57ec47adf98680254fa481fb91d5a98dea8f032e
|
|
!referencetests:229377
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: Ia9b360b4a057fe7bbce5b268092627c09a0dba82
|
|
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Change-Id: Ic7abe5dad700fbdc1b7cbab6936b52554f0a0360
|
|
threshold time
Signed-off-by: Nikhil Raj <nikraj01@e110586.galway.arm.com>
Change-Id: I4e5f96cb3a843a4ae29bad539c0eed42282344a8
|
|
!android-nn-driver:2572
Change-Id: I8fe52ceb09987b3d05c539409510f535165455cc
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
Change-Id: Ia25f919e45a210e1e2d5d50b0c9098bf01d88013
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
!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: I595b89dcb6419f7cb73cee51705b90f6eec7088b
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
Change-Id: I593e2540bd870d70aabb2c959f4e63a899967269
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
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
|
|
* 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
|
|
* 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>
|
|
* 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>
|
|
* 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>
|