Age | Commit message (Collapse) | Author |
|
* Moved deprecated functionality to its own heading
* Updated documentation for many of the parameters
* Added information on execution time versus inference time
Signed-off-by: Tracy Narine <tracy.narine@arm.com>
Change-Id: If017e49e7f6c60a72fe948c1cfa1a6f6a5c4a692
|
|
* Check if preferred backends have FP16 support before enable fp16-turbo-mode
* Unit tests
* Replaced global gpuAccCapabilities with getter method construction
* Replaced deprecated function call in SL shim
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Signed-off-by: Ryan OShea <ryan.oshea3@arm.com>
Change-Id: If29b62b330ca8987de8acf6408db11daf25ca0b5
|
|
* 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
|
|
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: Ibdded86713368ecfdf31c4118dfe8a3404d1e3b8
|
|
!android-nn-driver:9431
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
Change-Id: I58143445b5c5cf2aafd0838156c9543adce21e6a
|
|
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
|
|
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: Ic6bbbaa04aabaa5c3fd525acd5121f07d3392120
|
|
- 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
|
|
* Add shorthand argument for no print
* Add Execute network option to reuse buffers
* Add new synchronous execute method to reuse buffers
Signed-off-by: Ryan OShea <ryan.oshea3@arm.com>
Change-Id: Ia7ee99b2ba9a21043c9575d7546bf25208357141
|
|
Change-Id: Ib038e7b2616195a64715e3a7126da1368bbca1d3
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
|
|
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
|
|
* Introduce a mechanism to construct a DelegateOptions from an
ExecuteNetworkParams.
* Modify ExecuteNetwork to use this constructed DelegateOptions.
Signed-off-by: Colm Donelan <Colm.Donelan@arm.com>
Change-Id: Ied663a1e00ac3eece42244ed313ddafd6d2ce078
|
|
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: I10fb010ee8d3f813d2264cefb526f352e30d7046
|
|
* 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
|
|
* Allows to supply different input data for every execution of a
model when using the 'iterations' option in ExecuteNetwork
* Removes the option 'simultaneous-iterations' because it's functionallity
is now covered by 'iterations'
* Adds a deprecation warning message to notify users
* Little refactor of warning messages
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: Ib3ab0d6533f6952bfee20d098a890b653c34cc12
|
|
* 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
|
|
* 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>
|
|
* 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: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ib00be204f549efa9aa5971ecf65c2dec4a10b10f
|
|
* Enable GPU profiling on ExecuteNetwork
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I57bb4eeb45674e5218fce7e67b9bddf16ba0894d
|
|
* 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
|
|
* 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: 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 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
|
|
* 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>
|
|
* Allow multiple backends to be defined seperately like
" --compute CpuAcc --compute CpuRef "
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: Ic2a827f6e3463a7413c98a7eefacef8864c1e87b
|
|
* 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
|