Age | Commit message (Collapse) | Author |
|
* Unified ArmNN's weight format to [ M, I, H, W ] for the depthwise convolution
* Added conversion utilities to permute/reshape the weights as appropriate
when using CL and Neon backends
* Updated the reference implementation of the convolution
* Updated the relevant unit tests accordingly
!android-nn-driver:459
Change-Id: I07d0818efa9d1ca1e5dad82983aac1fe78eadb18
|
|
* Allow control inputs from TensorFlow graph but ignore them in ArmNN graph.
* Add utility function to test ArmNN graph structure.
* Add ArmNN graph structure tests in TensorFlow paresr to ensure that control inputs
are ignored in ArmNN graph as well as their inputs that are not used anywhere else.
Change-Id: Ib0ea0d2df85e3fc79b748fa4c9d20e0649352bc1
|
|
Change-Id: Ifd28e049192e6f5fe5c0f5d358afb2b530eef882
|
|
* Modified optimizer to support debug mode via DebugLayer
Change-Id: Ic8f313778e55540c182cf99876c44a0823be04c6
|
|
* Since DataLayoutIndexed is now required in the TF parser, this
changes move it to the armnnUtils library so that it'll be
accessible by the armnnTfParser
* Modified CMake files and Android.mk files accordingly
Change-Id: Ie2620359ef288aeff64cb9e9bec068a466eee0e9
|
|
workloads and workload functions
Change-Id: I6f3fce12a55f7d38ceafcdfcd6b5181bf56e2c09
|
|
* helper methods for creating TensorShape and TensorInfo objects
Change-Id: I371fc7aea08ca6bbb9c205a143ce36e8353a1c48
|
|
Change-Id: If8d8087d9d365e467d3ca9bf9c40d7219cb75cfd
|
|
* Add LayerTests
* Add WorkloadTests
!android-nn-driver:166
Change-Id: I903461002879f60fc9f8ae929f18784e2d9b1fc1
|
|
* Ported Google's LSTM implementation to RefLstmFloat32Workload
* Fixed the code throughout because of an error in the docs around the
scratch buffer size
* Updated IsLstmSupported
* Added the unit tests
!android-nn-driver:127
Change-Id: I5577b7e39ca52df1a7f102a9b437df6aa99520b6
|
|
stable test (memory-wise)
This prevents false-positives when running the tests on Master
Change-Id: I4348378f3689cb3ec98686a93315d2b88bb7bcc7
|
|
Change-Id: Idc0f94590566ac362f7e1d1999361d025cc2f67a
|
|
BatchToSpaceNdLayer.
* added Unit test
Change-Id: I80f55e8c7afb39d96006c8dd027fc9683ea8182e
|
|
Change-Id: I93223c8678165cbc3d39f461c36bb8610dc81c05
|
|
Change-Id: I663a0a0fccb43ee960ec070121a59df9db0bb04e
|
|
* Fixes bug when calcuating indexes for NHWC in
Pooling2D CpuRef implementation, it now uses
TensorBufferArrayView.
* Adds 2-Channel unit tests for Pooling2d on CpuRef,
Cl and Neon. The single channel tests were not
properly exercising Pooling2d using NHWC data layout.
* Refactors Pooling2D NHWC tests so that the input and
output data are permuted to NHWC when necessary,
instead of hard coding the data in NHWC format.
Change-Id: I5b9d41ed425ff283ea8c8ef6b1266ae0bc80f43b
|
|
shape in ValidateTensorShapesFromInputs
* Convolution2dLayer
* DepthwiseConvolution2dLayer
* Pooling2dLayer
* ResizeBilinearLayer
* Unittests for ValidateTensorShapesFromInputs
Change-Id: I057caf8a90d822175a7dd7271f960b65c6154bb4
|
|
Change-Id: Iae9a76b10d84d7ba80136b54355f8d37d2df475d
|
|
the unit tests
* Created the ClFloatWorkload class
* Added ClMeanValidate validation function
* Added helper function to convert the reduction axes from the ArmNN
format to ACL's
* Added workload tests
* Added some unit tests
* These changes need the CL pin to be pointing at least to revision
88d871028eeae57f9e4536d0329110eccb5e2890 (COMPMID-1574 Implement
ReduceMean in OpenCL)
!android-nn-driver:155033
Change-Id: I694fd36be0458c90e158172afde045fcc88c32ae
|
|
Change-Id: I45fd5b6dd32c435b78a54dc377a623e60978ce13
|
|
Change-Id: I44a9d26d1a5d876d381aee4c6450af62811d0dbb
|
|
src/armnn/test folder to the backends
* Moved backend-specific memory leak checking tests from RuntimeTests.cpp to
the corresponding backend test folder
Change-Id: I0a7f4ef52c5350c3cebca23b2b4e61a9446ca11f
|
|
Change-Id: Ie7549fd27378acfa97e68d098e338b8c9d4ea5d2
|
|
* Adds implementation to plumb DataLayout parameter
for Pooling2D on CpuRef.
* Adds unit tests to execute Pooling2D on CpuRef
using NHWC data layout.
* Refactors original tests to use DataLayoutIndexed
and removes duplicate code.
Change-Id: Ife7e0861a886cf58a2042e5be20e5b27af4528c9
|
|
Change-Id: I962e986607e5d045cd97b9eaeaea2f5ae624db35
|
|
Change-Id: I76551d511ef718eac36e5b8e5fe426ec3a402855
|
|
ref BatchNormalization
* Added create workload unit tests for the NHWC data layout
Change-Id: I03d66c88dc9b0340302b85012cb0152f0ec6fa72
|
|
ref Normalization
* Added create workload unit tests for the NHWC data layout
Change-Id: Id4813105c027a26e277de64fecea1845fea39fd9
|
|
Change-Id: I558a9a007604afc55e536d877f8da7d0215cc9c3
|
|
Change-Id: I3e6e5b9a62f30d03c05bd7178adea8f4c8275da8
|
|
* Adds implementation to plumb DataLayout parameter
for ResizeBilinear on CpuRef.
* Adds unit tests to execute ResizeBilinear on CpuRef
using the NHWC data layout.
* Adds DataLayoutIndexed API, allowing easy access to
the Channels, Height and Width of a tensor based on
its data layout. This reduces code duplication.
* Refactors original ResizeBilinear implementation and
tests to use the DataLayoutIndexed API when required.
Change-Id: Ic2b8916cdd2e370d070175547079d774daf6d7bf
|
|
* because it was added by mistake, assuming it was released in 18.08
which is not the case
Change-Id: I9c288eba56f3f6192007f79db884b255a14456e4
|
|
* Applying the proper tensor shape during the tests depending on
the specific data layout used
Change-Id: I9c6c1e077236e84cecc1e10d7b2d0bd901df3ebd
|
|
Change-Id: I8eca81d2e0780390eaa837c186ffe1c7d41fdebe
|
|
* Now hand in an optional vector of strings to Optimize
function in which errors/warning messages are placed.
* Optimize function changed to check outputs of each
layer. If they are Quantized 8 bit but the scale has
not been set an error message is added for each such output.
* Unit test modelled on defect report added to exercise the fix.
!android-nn-driver:152483
Change-Id: If9901f5324a516f1ab62858266b38f98dae16201
|
|
Change-Id: Ie02ccbd5945cbacd609b3b5d8d746c202c8e9c69
|
|
Change-Id: Ief0c91ba9abc2578944860ddbd3c19e2bad465bd
|
|
Change-Id: Ib38a6216ebcdc350c75c028951b3f18f36a2f6b7
|
|
IVGCVSW-1964 : Optional to support passing references
Change-Id: I4bf8c264d1726aab7e417de5ffd7d04248332e54
|
|
* Adds five unit tests that execute ResizeBilinear
with the NHWC data layout and Float32 data type.
* Refactors original ResizeBilinear Float32 tests
to take DataLayout as a parameter.
* Adds four unit tests that execute CreateWorkloadCl
for both NCHW and NHWC (NCHW tests did not exist
for CreateWorkloadCl).
Change-Id: I1af419ed0b62b8f4d4550f6d120a584a0a223b17
|
|
!android-nn-driver:151788
Change-Id: Ibdc41d09b8df05e7a0360dcb8a060860dfb1bd99
|
|
Change-Id: Iaadee0a08c0594c9a3c802a48fe346e15f2cbbb2
|
|
Change-Id: Iea941c1747454f5a4342351e4e82b10ffb9ccbbd
|
|
* Added RefPermuteFloat16Workload to serve as a fallback when CL
does not support the required permute configuration for FP16
* Move Half.hpp to armnnUtils as the utils library should not be
including private header files from the armnn library
Change-Id: Ibf0f698451e8406f7ed7cce470dab60b6d16361d
|
|
* moving backends/ClWorkloads to backends/cl
* and moving pure Cl workload related code to
backends/cl/workloads
Change-Id: I019a3c6b4da5e7a23074bf03fb057e63199ad129
|
|
* Added L2NormalizationDescriptor struct with m_DataLyaout member
* Updated all IsL2NormalizationSupported calls to take a descriptor
as an argument
* Updated L2NormalizationLayer to take a descriptor as an argument
!android-nn-driver:150116
Change-Id: I0459352d19cfd269bc864a70cf73910bf44fdc01
|
|
Change-Id: I6fb15c407024e3b91d5abf4513f8090be5821760
|
|
armnn:149855
Change-Id: I26e8cf83422a65049386a5ebdb6d0001627aefaa
|
|
* Reference backend is renamed to backends/reference as per
https://confluence.arm.com/display/MLENG/Pluggable+backends
Change-Id: I27a13c274eb60995dfb459e3c49c0e2f60bcd32c
|
|
WallClockTimer interface
Change-Id: Ia90b709ddfff321dbc218add4ab19737f68a44bf
|