aboutsummaryrefslogtreecommitdiff
path: root/src/armnn/test
AgeCommit message (Collapse)Author
2018-11-16IVGCVSW-2092 Port LSTMCell::Eval to ArmNNMatteo Martincigh
* 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
2018-11-15Adedd load/unload warm-up before the memory lek test to put the runtime into aMatteo Martincigh
stable test (memory-wise) This prevents false-positives when running the tests on Master Change-Id: I4348378f3689cb3ec98686a93315d2b88bb7bcc7
2018-11-15IVGCVSW-2136: Remove memory management methods from workload factoriesAron Virginas-Tar
Change-Id: Idc0f94590566ac362f7e1d1999361d025cc2f67a
2018-11-14IVGCVSW-2054: Fixing issue with InferOutputShape implementation in ↵Éanna Ó Catháin
BatchToSpaceNdLayer. * added Unit test Change-Id: I80f55e8c7afb39d96006c8dd027fc9683ea8182e
2018-11-13IVGCVSW-2066: Add IMemoryManager and integrate into the backends frameworkAron Virginas-Tar
Change-Id: I93223c8678165cbc3d39f461c36bb8610dc81c05
2018-11-02IVGCVSW-1946: Remove armnn/src from the include pathsAron Virginas-Tar
Change-Id: I663a0a0fccb43ee960ec070121a59df9db0bb04e
2018-10-31IVGCVSW-2102: Fix Pooling2D CpuRef indexing bugJames Conroy
* 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
2018-10-27IVGCVSW-2083 - Add DataLayout parameter to calculate the expected output ↵narpra01
shape in ValidateTensorShapesFromInputs * Convolution2dLayer * DepthwiseConvolution2dLayer * Pooling2dLayer * ResizeBilinearLayer * Unittests for ValidateTensorShapesFromInputs Change-Id: I057caf8a90d822175a7dd7271f960b65c6154bb4
2018-10-26IVGCVSW-1896 : SubGraph selectorDavid Beck
Change-Id: Iae9a76b10d84d7ba80136b54355f8d37d2df475d
2018-10-25IVGCVSW-2049 + IVGCVSW-2051 Create the CL Mean Float workload and addMatteo Martincigh
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
2018-10-25IVGCVSW-2073: Move remaining backend-specific tests from armnn to backendsAron Virginas-Tar
Change-Id: I45fd5b6dd32c435b78a54dc377a623e60978ce13
2018-10-25IVGCVSW-2071 : remove GetCompute() from the WorkloadFactory interfaceDavid Beck
Change-Id: I44a9d26d1a5d876d381aee4c6450af62811d0dbb
2018-10-22IVGCVSW-2060: Separate and move backend specific unit tests from the ↵Aron Virginas-Tar
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
2018-10-22IVGCVSW-2019 : replace Compute enum in the backend preferences listDavid Beck
Change-Id: Ie7549fd27378acfa97e68d098e338b8c9d4ea5d2
2018-10-22IVGCVSW-2024: Support NHWC for Pooling2D CpuRefJames Conroy
* 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
2018-10-22IVGCVSW-2023 CL and Neon implementation of BatchNorm with NHWCNikhil Raj
Change-Id: I962e986607e5d045cd97b9eaeaea2f5ae624db35
2018-10-22IVGCVSW-2019 : replace Compute enum in the Layer objectDavid Beck
Change-Id: I76551d511ef718eac36e5b8e5fe426ec3a402855
2018-10-22IVGCVSW-2040 Add unit tests for the newly implemented NHWC support inMatteo Martincigh
ref BatchNormalization * Added create workload unit tests for the NHWC data layout Change-Id: I03d66c88dc9b0340302b85012cb0152f0ec6fa72
2018-10-22IVGCVSW-2033 Add unit tests for the newly implemented NHWC support inMatteo Martincigh
ref Normalization * Added create workload unit tests for the NHWC data layout Change-Id: Id4813105c027a26e277de64fecea1845fea39fd9
2018-10-22IVGCVSW-1938: Move backend-specific source files to the corresponding backendAron Virginas-Tar
Change-Id: I558a9a007604afc55e536d877f8da7d0215cc9c3
2018-10-22IVGCVSW-1922 Unit test for DepthwiseConvolution with NHWCNikhil Raj
Change-Id: I3e6e5b9a62f30d03c05bd7178adea8f4c8275da8
2018-10-22IVGCVSW-1978: Support NHWC for ResizeBilinear CpuRefJames Conroy
* 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
2018-10-22IVGCVSW-1969 : remove boost::optional compatibility from ArmNN OptionalDavid Beck
* because it was added by mistake, assuming it was released in 18.08 which is not the case Change-Id: I9c288eba56f3f6192007f79db884b255a14456e4
2018-10-22IVGCVSW-1967 Fix L2Norm NHWC unit testMatteo Martincigh
* Applying the proper tensor shape during the tests depending on the specific data layout used Change-Id: I9c6c1e077236e84cecc1e10d7b2d0bd901df3ebd
2018-10-22IVGCVSW-1988: Refactor backend-specific unit testsarovir01
Change-Id: I8eca81d2e0780390eaa837c186ffe1c7d41fdebe
2018-10-10IVGCVSW-1929: Fix for this defect (QASYM8 no scale)jimfly01
* 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
2018-10-10IVGCVSW-1974 - Update CreateWorkload test CL and NeonFrancis Murtagh
Change-Id: Ie02ccbd5945cbacd609b3b5d8d746c202c8e9c69
2018-10-10IVGCVSW-1982 - add create workload test for 2D Pooling (NHWC data layout)Nina Drozd
Change-Id: Ief0c91ba9abc2578944860ddbd3c19e2bad465bd
2018-10-10IVGCVSW-1975 : total removal of boost::optional from the public interfaceDavid Beck
Change-Id: Ib38a6216ebcdc350c75c028951b3f18f36a2f6b7
2018-10-10IVGCVSW-1975 : Remove boost::optional from the public interfaceDavid Beck
IVGCVSW-1964 : Optional to support passing references Change-Id: I4bf8c264d1726aab7e417de5ffd7d04248332e54
2018-10-10IVGCVSW-1932: Add Unit tests for NHWC ResizeBilinearJames Conroy
* 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
2018-10-10IVGCVSW-1964 : replace optional biases with home-grown OptionalDavid Beck
!android-nn-driver:151788 Change-Id: Ibdc41d09b8df05e7a0360dcb8a060860dfb1bd99
2018-10-10IVGCVSW-1642 : introducing the IBackend interfaceDavid Beck
Change-Id: Iaadee0a08c0594c9a3c802a48fe346e15f2cbbb2
2018-10-10IVGCVSW-1920 Unittests for NHWC Normalization Workloads and Layernarpra01
Change-Id: Iea941c1747454f5a4342351e4e82b10ffb9ccbbd
2018-10-10IVGCVSW-1913: Fix for ValidationTest.concat_float_3_relaxedarovir01
* 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
2018-10-10IVGCVSW-1900 : CL backend folder structureDavid Beck
* moving backends/ClWorkloads to backends/cl * and moving pure Cl workload related code to backends/cl/workloads Change-Id: I019a3c6b4da5e7a23074bf03fb057e63199ad129
2018-10-10IVGCVSW-1863 Support NHWC for L2NormalizationMatteo Martincigh
* 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
2018-10-10IVGCVSW-1812 Adding Ref implementation and tests of MeanWorkloadsnarpra01
Change-Id: I6fb15c407024e3b91d5abf4513f8090be5821760
2018-10-10IVGCVSW-1899 : Neon backend folder structureDavid Beck
armnn:149855 Change-Id: I26e8cf83422a65049386a5ebdb6d0001627aefaa
2018-10-10IVGCVSW-1898 : Ref backend folder structureDavid Beck
* Reference backend is renamed to backends/reference as per https://confluence.arm.com/display/MLENG/Pluggable+backends Change-Id: I27a13c274eb60995dfb459e3c49c0e2f60bcd32c
2018-10-10IVGCVSW-1821 - taking out scale factor again as it's polluting the ↵Nina Drozd
WallClockTimer interface Change-Id: Ia90b709ddfff321dbc218add4ab19737f68a44bf
2018-10-10IVGCVSW-1821 - update NEON workload utils to use timers in correct order, ↵Nina Drozd
updated units used in NeonTimer Change-Id: I593af42bd2930dd9d147354b706087e3ac260fe9
2018-10-01IVGCVSW-1802 : Neon Sub WorkloadDavid Beck
Change-Id: I1e914b046cd8fd25669390d477f101098fe0d476
2018-09-25IVGCVSW-1801 : Cl implementation for SUBDavid Beck
Change-Id: Ia2e1dda8653197454a50679d49020397f5327979
2018-09-17IVGCVSW-1807 : change license text in file headersDavid Beck
All changes are the same: // // Copyright © 2017 ARM Ltd. All rights reserved. -// See LICENSE file in the project root for full license information. +// SPDX-License-Identifier: MIT // Change-Id: I37eae011411133663ca9d2b059714d92f8bf8e24
2018-09-17IVGCVSW-1786 - Division by zeroFrancis Murtagh
* Added logic for different cases of division by zero for ref * Added DivisionByZeroTest * Updated SelectiveComparer to compare NAN and INFINITY Change-Id: Iec6f89264b17a0b03fad5d7ec4b2dafc31fea5df
2018-09-17IVGCVSW-1200 Division layerFrancis Murtagh
*IVGCVSW-1772 Create QueueDescriptors *IVGCVSW-1773 Add a CL implementation of the DivisionWorkload *IVGCVSW-1774 Add Neon implementation of the DivisionWorkload *IVGCVSW-1775 Add a Ref implementation of the DivisionWorkload *IVGCVSW-1776 Add a Division Layer * Added simple division unit tests with broadcasting Change-Id: I05751fb7f868789f6c06f91e8d25e52b4f12ab5e
2018-08-31Release 18.08telsoa01
2018-05-23Release 18.05surmeh01
2018-03-29Release 18.03surmeh01
generated by cgit v1.2.1 (git 2.23.0) at 2024-07-03 04:41:08 +0000