aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2018-10-30MLCE-67 Fix for Github issue 91Matthew Bentham
Remove incorrect early out from image resize Change-Id: I58014680f5cbe43dfc6b4af66638db67c070a146
2018-10-29IVGCVSW-2029 Tweak results handling for batch size 2 testMatthew Bentham
When looking for the top probability, use the 'first' result not the 'second'. This avoids an issue where for batched tests the classification index was reported wrongly. Still doesn't correctly handle multiple results with the exact probabibility, or batched testing, but it's slightly more correct than before. Change-Id: I57d33552754667613e222d9d2037e12c87a96854
2018-10-29IVGCVSW-2074: Updated DepthwiseConvolution2dAsymmetricTest for NHWCjimfly01
Change-Id: I1bc8d2f270d4abfaa62e4843b8d96bcf462c6b09
2018-10-29Fixed Android32 build error blocking masterMatteo Martincigh
* In ImagePreprocessor, typecasted the number of image elements (unsigned int) to a const_iterator::difference_type (int) Change-Id: Idb8611185f6471751678a0a77d8225bceb204a34
2018-10-29Fixed backend id argument parsing in ExecuteNetworkMatteo Martincigh
Change-Id: I99498a633d75a2b4bdcd059627b07beaa9984890
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
2018-10-26IVGCVSW-2069 - Implement NHWC Convolution2D for CpuRefnarpra01
* Calculate index for NHWC to compute Convolution * add more unit test for NHWC Change-Id: I800d649b9b42be2758c445e3b3e76142888c1377
2018-10-26IVGCVSW-2081: Move generic backend tests to the backend related CMake filesAron Virginas-Tar
Change-Id: Ib642b0c983fed21cf38be8233bd13d86f4bf413d
2018-10-26IVGCVSW-2029 Fix fully connected layer support in TfLite Parser and ↵Nattapat Chaimanowong
implement test for TfLite VGG16 quantized Change-Id: I2061f62f62684b963fa0f090718f1dcffe5c93ce
2018-10-26IVGCVSW-2056 + IVGCVSW-2064 : move ClContextControl to the ClBackendDavid Beck
Change-Id: Ice19d3f763298bc14585267df389e99df846320d
2018-10-26IVGCVSW-2074: SimpleConvolution2dTestImpl updated for NHWCjimfly01
* Added a defaulted DataLayoutIndexed argument to the SimpleConvolution2dTestImpl * Permute test data tensors just before use if necessary * Add DataLayout to descriptor * Added a DataLayoutIndexed argument to SimpleConvolution2d3x5TestCommon * Added NHWC versions of the SimpleConvolution2d3x5Test for Neon and CL Change-Id: I10e3ece42a50108baeabe4d8b0f0ac3e6d532261
2018-10-25IVGCVSW-2051 Fixed the dynamic allocation of the dimSizes array in MeanLayerMatteo Martincigh
Change-Id: I6e39f1e1bc32c0c2c1953da00016edd68c48d4e0
2018-10-25IVGCVSW-2057: Remove ARMCOMPUTE(CL/NEON)_ENABLED and ARMCOMPUTENEON_ENABLED ↵Aron Virginas-Tar
from src/armnnTfliteParser/test/ParserFlatBufferFixture.hpp Change-Id: I85c720d37097e0c9a53dc473a7eac09f21deb847
2018-10-25IVGCVSW-2058: Remove ARMCOMPUTE(CL/NEON)_ENABLED and ARMCOMPUTENEON_ENABLED ↵Aron Virginas-Tar
from src/armnnUtils/ParserPrototxtFixture.hpp Change-Id: Ief836fb80c4c966f1b76c9429d4a7fb644ceb73d
2018-10-25IVGCVSW-2059: Remove CL-specific code from ProfilerAron Virginas-Tar
Change-Id: I279986b83c7a38b6d395f8a496382ffaebb9ed08
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-1007 Support Inception-V3 and V4 in CaffeParserMohamed Nour Abouelseoud
Removed the kernel dimension/range validation from CaffeParser Change-Id: I9e63c01fecbaea1448aa203e7212cd4aac854c3d
2018-10-25IVGCVSW-2071 : remove GetCompute() from the WorkloadFactory interfaceDavid Beck
Change-Id: I44a9d26d1a5d876d381aee4c6450af62811d0dbb
2018-10-25IVGCVSW-2067 : dynamically create workload factories based on the backends ↵David Beck
in the network Change-Id: Ide594db8c79ff67642721d8bad47624b88621fbd
2018-10-25IVGCVSW-2053: Validate BackendId parameters for the InferenceTest (EndToEnd ↵Aron Virginas-Tar
tests) / ExecuteNetwork !referencetests:154790 Change-Id: Iaf9608ae1e66460079f2546b30d7fbc9b55bb7dd
2018-10-25IVGCVSW-2026 + IVGCVSW-2027 Add FullyConnected Support to TfLiteParserSadik Armagan
Change-Id: Id48f97ee33e2fd650a1ee3365ef66bdfc514a586
2018-10-22IVGCVSW-1823 *Free working mem only when network changesDerek Lamberti
Change-Id: I62b34713f8ebd96b9d4369f25cc8ba474aad8bb4
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-2063 Documentation for new operations in TfLite ParserSadik Armagan
* Updated TfLite Parser read me file for new operations added Change-Id: Idd4dcbe03ee8cd8c65377e03b6e52f3766312b70
2018-10-22IVGCVSW-1991 : refactor m_SupportedComputes in DeviceSpecsDavid Beck
Change-Id: Ied3d54dc356f5e4f87aeb59f66423ac1f893dd01
2018-10-22IVGCVSW-1955: Unify backend exceptions (wrap cl::Error)Aron Virginas-Tar
* Added wrapper function around arm_compute::IFunction::run() that catches cl::Error and wraps it into an armnn::RuntimeException * Added MakeWorkload template inside ClWorkloadFactory that catches cl::Error and wraps it into an armnn::RuntimeException * Replaced cl::Error with armnn::RuntimeException in catch statements inside LoadedNetwork Change-Id: I2340f41ae02b8db1d7ef5157824a50e7410854e3
2018-10-22IVGCVSW-2019 : replace Compute enum in the backend preferences listDavid Beck
Change-Id: Ie7549fd27378acfa97e68d098e338b8c9d4ea5d2
2018-10-22IVGCVSW-2061: Add ARMNN_SCOPED_PROFILING_EVENT_CL inside ↵Aron Virginas-Tar
ClLstmFloatWorkload::Execute() Change-Id: Ia3f895474b54e73711feb9795e7d47cbd61f13a3
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-2013 Add a UInt8 Reference Implementation for the PAD OperatorMohamed Nour Abouelseoud
Change-Id: I41f3606198db1fda8d72aaf5169594ba9156eb38
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-2005: Pull in backend specific unit tests into Android.mk similarly ↵Aron Virginas-Tar
as backend sources Change-Id: Icafc644b64c591f4dc0e1560d02b806bf053a2da
2018-10-22IVGCVSW-2030 and IVGCVSW-2031 Add MaxPooling support and unit test to TfLite ↵Nattapat Chaimanowong
Parser Change-Id: I3aea8ea6d018900682d278f28a50e40cf2f963fe
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-1865 - Support NHWC for Convolution2D (CpuRef)Nikhil Raj
* Updated the ConvImpl.hpp to use DataLayoutIndex * Enabled unit test for CpuRef * Update CreateWorkload Tests for ref with NHWC Change-Id: Id309b7ef677489d63dcb5e09bd48ab9624b5ebfb
2018-10-22IVGCVSW-2037 : separate registry for layer support intrefacesDavid Beck
* because their lifetime is different from backends Change-Id: I9ba525e7e503b148cde1294933f3954b8bad3d68
2018-10-22IVGCVSW-2032 + IVGCVSW-2033 Add NHWC implementation to the referenceMatteo Martincigh
Normalization workload * Enabled NHWC support in RefNormalizationFloat32Workload for Across normalization * Added unit test for the reference implementation Change-Id: I0e1f319e76491d43b83b121c273fadb5b259d1a0
2018-10-22IVGCVSW-2038 + IVGCVSW-2039 + IVGCVSW-2040 Add NHWC support to the Float32 ↵Matteo Martincigh
and UInt8 BatchNormalization workloads * Enabled NHWC support in RefBatchNormalizationFloat32Workload * Added NHWC unit tests for both FP32 and U8 * Refactored the existing unit tests Change-Id: I6aa18f1dcc0666b80a17a7ed229cf53607bae147
2018-10-22IVGCVSW-2012: Remove check for DataType::QuantisedAsymm8 in NeonLayerSupportAron Virginas-Tar
Change-Id: Ifeabb8c6aa02b5209245d863fc0d7aeceb25cb30
2018-10-22Added missing pragma directive to TensorBufferArrayView.hppMatteo Martincigh
Change-Id: Ic7882cb415ccb7a899f5fb353fb96a1f19d03346
2018-10-22IVGCVSW-1951 Remove type templating from NeonDepthwiseConvolutionWorkloadNattapat Chaimanowong
Change-Id: I411d02949524eb802672d83ee281300c34b007c8
2018-10-22IVGCVSW-1951 Remove type templating from NeonConvolution2dWorkloadNattapat Chaimanowong
Change-Id: Id3d8137d60b14e93863ad5b6db752a7f6ef9b7fb
2018-10-22IVGCVSW-2022 : fix for backend cmake files to respect BUILD_UNIT_TESTS variableDavid Beck
Change-Id: I8d34419742152edd50f1ec438e32d3ccc4f38351
2018-10-22Fixed unsigned to signed conversion warningKohei Takahashi
Change-Id: I6ff147e4418e8d0252bedfd1cf4a3bc3bc38ada7
2018-10-22IVGCVSW-2018 Support NHWC in the current ref implementationMatteo Martincigh
* Enabled the now supported ref layer tests * Re-enabled the failing test now that the bug has been fixed in ACL 1903a9976ae24f40cb2203364211ed62fcfbb985 * Added CreateWorkload test for ref L2Normalization NHWC * Refactoring the ref L2Normalization for clarity !armnn:153723 Change-Id: Id0067e49072b3e057ffe3ae3b70d928be6091c0f
2018-10-22IVGCVSW-1951 Update NeonWorkloadUtilsNattapat Chaimanowong
Change-Id: I147dbf6811f84ec4588264d636a36efc8ec56f72
generated by cgit v1.2.1 (git 2.23.0) at 2024-07-02 19:19:19 +0000