Age | Commit message (Collapse) | Author |
|
* Conv3d is only correctly supported for external delegates
from TF v2.6, as there was a breaking bug in v2.5.
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: Ib7941307f4c7b0d3dbb7deaa5a90aceb63c1162f
|
|
* Adding Runtime parameter: dynamic-backends-path
* Add profiling parameters:
gpu-enable-profiling,
enable-internal-profiling, internal-profiling-detail,
enable-external-profiling, timeline-profiling, outgoing-capture-file,
incoming-capture-file, file-only-external-profiling,
counter-capture-period, profiling-file-format
* Adding utility parameter "serialize-to-dot"
Signed-off-by: Colm Donelan <Colm.Donelan@arm.com>
Change-Id: Ibff4b9a85ff0f0da5d70e8aa0bb6cba96aaabbc3
|
|
* Tflite parser
* Tflite delegate
* Serializer
* Deserializer
* Ref, CpuAcc and GpuAcc workloads
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I601a9ee1680b372c7955d9a628857d08c3cfd377
|
|
to Ref backend and armnn delegate
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I203d0029c12221228ffe229acda3c90594394e9b
|
|
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: Ib04f8d6b9e60a4204c56eba4c2ecd2b316509dcc
|
|
* Constant weights and biases are now stored as Constant layers.
* Updated Serializer, Deserializer and unit tests to reflect this.
* Updated TfLiteDelegate, TfLiteParser and OnnxParser.
* Updated Schema with IsConstant and ConstantTensorsAsInputs.
* Updated Ref backend to handle constant weights and
bias as inputs rather than reading from member variables.
* Added dynamic or constant input EndToEnd tests.
!android-nn-driver:5959
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: Ibf3cf437df1100e4b322b0d303c575c6339f9696
|
|
* Add TfLiteParser and delegate support
Signed-off-by: Keith Davis <keith.davis@arm.com>
Change-Id: Id3219ba7cc7128b5e73de2c7d8d076a40dcce9c5
|
|
profiling common
!android-nn-driver:5691
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ib71af0831e324ac6bd27b1a36f4a6ec1a703b14a
|
|
* Alpha is supported both as a constant and as an
input tensor.
Signed-off-by: James Conroy <james.conroy@arm.com>
Change-Id: I20f30d479b87dc5fbcf75a1ce5305d70ae9b0646
|
|
* Determine Splitter outputs to correctly perform validation
* Add validation for a Reshape Layer
* Add back the Num6 Axis2 test to CpuAcc and GpuAcc
Signed-off-by: Kevin May <kevin.may@arm.com>
Change-Id: I1e8108ce50d81420057d7a8b098a07eda63c5c8d
|
|
* Remove unsupported Delegate Unit Tests for CAST and UNPACK
Signed-off-by: Kevin May <kevin.may@arm.com>
Change-Id: I03e460a77ee54e63e024d58e8f032246eaa9bac3
|
|
Signed-off-by: Kevin May <kevin.may@arm.com>
Change-Id: I23731718236043b46c143eaf416cb375edd93983
|
|
* Added support for PACK which is equivalent to Arm NN STACK
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: I9ea134d0310eeea1caba30a8b9221712e9487c75
|
|
* Refactored the code for checking constant inputs.
* Added a unit test for ADD operator with constant input.
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: Ie7207e5a1ce77ea305552859de32a66e07c68a6f
|
|
* with Conv2D for tflite parser and delegate
* with TransposeConv for tflite parser
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: I8d1ed1f3388c6eace436d0e6fd5869451c6e7830
|
|
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>
|
|
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I6da711950b8e7d3c0d5cbd443e91eb36700ac4c8
|
|
* Reading tensor infos won't allow a permutation vector anymore.
The permutation only changed the quantization dimension not the
shape and was therefore misleading
* The permutation of the full tensor info is now performed in
armnnUtils::Permuted
* Changed TfLite Parser depthwise parsing function
* Added unit tests to TfLite Parser with more random data
* Changed TfLite Delegate depthwise parsing function
* Added unit test to the delegate with per channel quantization
!android-nn-driver:5412
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: I1f985ee69547bcaf16a72201e00a6b6fe1ef9a97
|
|
Signed-off-by: Keith Davis <keith.davis@arm.com>
Change-Id: I2873f8563cc11da550d460b04e5175372489a564
|
|
TfLiteDelegate support for FullyConnected Operator'
* Added front-end support for non-const weights for FULLY_CONNECTED operator
* Added FULLY_CONNECTED end-to-end test
* Updated FULLY_CONNECTED operator support in TfLite Arm NN Delegate for non-const weights
* Updated the version numbers
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: Iffa5b9aa9297aca4c02d923cce4636c88ac21faa
|
|
* Added FILL operator to TfLite ArmNN Delegate
* Added unit tests
Signed-off-by: David Monahan <david.monahan@arm.com>
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I335ef469ff773fa4305eb87f6e93ae9c03fc6997
|
|
* Add LSTM operator
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: If8c667685fa1176738ffe2e6d08b1c684e7ee6b2
|
|
* add template specialization declaration to header to resolve clang issue
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: Id8104d6feda19ed3f5f0cb018d719b1677772d9b
|
|
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: Icd87b1c54e1a5de84893882da30840a9097f6d84
|
|
* 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 support for BATCH_TO_SPACE_ND and SPACE_TO_BATCH_ND
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: Ib29333f3e2bc1a18bcc63533da4369b63c45ab90
|
|
* Added FLOOR operator support to Arm NN TfLiteDelegate
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I986ce8c5a825f509e0f8b3d257fd5b60834c322f
|
|
* Added TfLiteParser support for REDUCE_MIN and REDUCE_MAX operators
* Added ACL workloads support for REDUCE_MIN, REDUCE_MAX, and REDUCE_SUM operators
* Added TfLite Delegate support for REDUCE_MIN, REDUCE_MAX, and REDUCE_SUM operators
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I8085d59946bfd4ab78a59a61f899031ae53371a8
|
|
* Add reduce-fp32-to-fp16, reduce-fp32-to-bf16, debug-data, memory-import
options to external delegate
* Simplify DelegateOptions
* Add test mock models
* Unit tests
* Configure lfs to manage tflite files
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I1e4db468862ba03d4cb031347bc307cf940b3cb1
|
|
Signed-off-by: Keith Davis <keith.davis@arm.com>
Change-Id: Ie8c03153f82434d73572278eedb8a4b5b89ed837
|
|
* Remove double brackets for scalars
* Add in extra location in cmake for tf lite dynamic library
Signed-off-by: Keith Davis <keith.davis@arm.com>
Change-Id: I31ef9a955d4677faabedc0068ae2cfbfe570b58c
|
|
* Added DEPTH_TO_SPACE and SPACE_TO_DEPTH operators support
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I2595f759181bd7339127e7b114b850b534210dd5
|
|
* Added L2_NORMALIZATION and LOCAL_RESPONSE_NORMALIZATION opertor support
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: Ic9e66879cf6469fa8761fb1c9dd5950771f629b0
|
|
* Add OptimizerOptions, NetworkProperties, DebugCallbackFunction
to DelegateOptions
* Enable OptimizerOptions when the network is being optimized
* Enable NetworkProperties when loading network
* Enable DebugCallbackFunction
* Add error message when loading network
* Log warning instead of error when operator is not supported but
could fallback to another backend
* Improve uint16_t CompareData
* Unit tests
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I353035afb442774bfeb1c62570a90755c2ceaf38
|
|
* Added ARG_MIN and ARG_MAX support to armnn_delegate
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: Ia000c4b64378e28320164edd4df2902ca13dcda6
|
|
* Float16 unit tests for Reshape
* Remove unsupported data type from Pad
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: Ib1804bb6e708a0552fb40d05fe8a6511936f9793
|
|
* Add Pad and PadV2 operators support to Armnn Delegate
* Add dimension check to CompareOutputData test utility
* Unit tests
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I9d00eb08f71e791498908fcbdb9de561e1c01aef
|
|
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I33eb8c650be654ad891afd2295f2057f13a9d084
|
|
* Enabled Hard Swish and Elu in TfLiteDelegate
* Added support for Elu in TfLiteParser
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: If09321b58568a98e14cabce610a1586556da041e
|
|
* Implemented Logical AND, NOT and OR operators.
* NOT uses existing ElementwiseUnary VisitLayer function & tests.
* AND/OR uses new LogicalBinary VisitLayer function & tests.
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: I5e7f1e78b30c36ac7f14c70a712b54f98d664b83
|
|
* Fix Arm Android Compiler errors
Signed-off-by: Keith Davis <keith.davis@arm.com>
Change-Id: If5fae0fda08b6102eb46217564a096f87a3b6740
|
|
* Added SPLIT and SPLIT_V support to armnn_delegate
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I2def9b8be783b25ef17a997e521c6027553035d3
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Iaf2112363d2b191327711d8e083fee2a751c35c5
|
|
* Correct filter shape for DepthwiseConv2d
* Remove non-support data type
* Allow check for flatten on Reshape
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: Ic4be63d7c2f3a2b5e13a1530025a49464c21171b
|
|
* Correct input shape
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I9d1fe4c8ef32a9dfba7f7fdd6af314e9a522fce8
|
|
* Changing Uint8 tests to Int8 for Delegate Transpose Conv2d
* Refactor of Quantization tests to be per backend
Signed-off-by: David Monahan <david.monahan@arm.com>
Change-Id: Ic1528e1dc339030c7f1eed9f3884e99b14f389e4
|
|
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: Ibfd1968a622c2538bbfacf4802cd45096de59db5
|
|
* Since NEON/CL do not support QSYMM16 for Quantization,
disabling related tests on both backends and running
on CpuRef only.
Change-Id: Ifbc44cdfb81f25587ef87af8c44243dd88bb25c3
Signed-off-by: James Conroy <james.conroy@arm.com>
|
|
* Apply new test suite structure to be able to filter for backends
For ElementwiseBinary and ElementwiseUnary
* Add tolerance to data comparison
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: Iccabb68f316c93533e1076da5822ebc199e23739
|
|
* Create backend test suite structure
* Add special compare function for boolean values
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: I55a2ae1ac6ad21cdcdd5ae99ef56ed00fa24776f
|