aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2018-11-19IVGCVSW-2043 - Merger using ACL for innermost concat axisNikhil Raj
* Add ClMergerWorkload and NeonMergerWorkload to call ACL for innermost concat axis * Modify layer support to call ClMergerWorkloadValidate and NeonMergerWorkloadValidate when concat axis is inner most * Add m_ConcatAxis to MergerDescriptor * Modify MergerQueueDescriptor::Validate to check sub tensor only when using subtensor !android-nn-driver:166 Change-Id: I56676b43964c8d6d726387b41b3cc34a512c0f0a
2018-11-19IVGCVSW-2167: Run parser unit tests on the reference backend onlyAron Virginas-Tar
Change-Id: Ib11c3d36c7109198da7266955414580e8fb916b5
2018-11-19Fix for Github issue #103Matthew Bentham
Use CMAKE_THREAD_LIBS_INIT instead of pthread in sample_app. The separate pthread library doesn't exist on Android. Change-Id: I9a363ba7d29d2673359349f5f4288844f0550946
2018-11-19Changed the mode of generate_tensorflow_protobuf.sh to executableMatteo Martincigh
Change-Id: I0042395b46906f70d09a16b4122af3d911f5a53d
2018-11-19IVGCVSW-2115: Updated README.mdjimfly01
* Added line to README.md explaining the function of the get_compute_library.sh script Change-Id: If6be1c64443dcd6d0a08a12485de3d38614542f0
2018-11-16IVGCVSW-2115: Script to clone/fetch correct clframeworkjimfly01
* Script designed to be invoked from anywhere clones clframework relative to where the script source is located in armnn/scripts * Allows user to specify GITHUB_USERNAME on command line with -g option otherwise will set this value to $USER Change-Id: I34ee0d936152e94ff16b9bd7751c3da7248c9150
2018-11-16IVGCVSW-2155 - Always call NEConvolutionLayer in NeonConvolution2dWorkloadnarpra01
* Remove check for preferDirectConvolution * Remove IsNeonDirectConvolutionPreferred * Remove unused tests and functions Change-Id: I3f0868f41403ec5fa740889e7bdcb4415ad77bda
2018-11-16IVGCVSW-2017: CLWorkload to use L2NormalizationFrancisMurtagh
* Changed ClL2Normalisation from using CLNormalizationLayer to use CLL2NormalizeLayer to normalise along the channel axis in either NCHW or NHWC format. Change-Id: I399cbee408a277d1ef8c6c85ebcbd86d6c3e407b
2018-11-16IVGCVSW-2158 BuildGuideCrossCompilation.md wrong protobuf versionFerran Balaguer
Change-Id: Ibe826db4412c54aba42c45c155e7e5329861bdb1
2018-11-16IVGCVSW-2162: Remove conditional compilation directives from ArmComputeUtilsAron Virginas-Tar
Change-Id: Ie2f134fd51de919c50fa9d8d82bbb4ed4ee46469
2018-11-16IVGCVSW-2157: Remove conditional compilation directives from ClBackendContextAron Virginas-Tar
Change-Id: I0b9818c3bc09101aa6563ea8e4a886483d3b09d1
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
2018-11-15IVGCVSW-2156: Remove conditional compilation directives from ClContextControlAron Virginas-Tar
Change-Id: I812d09a869fe7c45ce71108fb675f3e2d974e2d9
2018-11-15IVGCVSW-2134: Updating version number to 18.11keidav01
Change-Id: I7cbfd5a6ab0746e0351b64a45617ed089992c1a9
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-2086: Add StridedSlice layer & corresponding no-op factory ↵Conor Kennedy
implementations Change-Id: I906dcb8b4c9b491bf3a661f208c09d0ea1c0fa35
2018-11-15IVGCVSW-2136: Remove memory management methods from workload factoriesAron Virginas-Tar
Change-Id: Idc0f94590566ac362f7e1d1999361d025cc2f67a
2018-11-15IVGCVSW-2064 + IVGCVSW-2066 + IVGCVSW-2125 + IVGCVSW-2128 backend docs updateDavid Beck
Change-Id: Iccc1272e59bd71c59f810a54d6d3742859789212
2018-11-15Fixed minor typos in BuildGuideCrossCompilation.mdMatteo Martincigh
Change-Id: I4d02a6cca8e99d70a389ca3b0ce47fb7f15ed21f
2018-11-14IVGCVSW-2152: Convert TfLiteParser to NHWCjimfly01
* Removed the convertFromTfToArmnnFormat flag from the CreateConstTensor and CreateConstTensorImpl functions * Removed the SwizzleInDeswizzleOut function and its invocations in the ParseConv2D, ParseDepthwiseConv2D and ParsePool functions. Change-Id: Id935e28ab6eff4731f838af9490d016e108f6df6
2018-11-14IVGCVSW-2125 : Consolidate backend registries into onejimfly01
* adding missing include <functional> into BackendRegistry.hpp Change-Id: I7a4ba867a856c90a3099a782ff41b8a5fb9a9efb
2018-11-14IVGCVSW-2054: Fixing issue with InferOutputShape implementation in ↵Éanna Ó Catháin
BatchToSpaceNdLayer. * added Unit test Change-Id: I80f55e8c7afb39d96006c8dd027fc9683ea8182e
2018-11-14IVGCVSW-2017: Refactored L2Normalisation Testsjimfly01
* L2Normalisation Tests now take the layout as an argument. Change-Id: Ib393889eedb3a81c9a500da91593e90a18549c33
2018-11-13IVGCVSW-2066: Add IMemoryManager and integrate into the backends frameworkAron Virginas-Tar
Change-Id: I93223c8678165cbc3d39f461c36bb8610dc81c05
2018-11-12Tidying up multiple issuesÉanna Ó Catháin
* Fixed error in InferOutputShape implementation * Added better error checking to the BatchToSpace implementation. * Added defaults to the batchToSpace descriptors. * Changed crops to be a vector of pairs to align with the SpaceToBatch implementation Change-Id: Ib1c16d871f0898a1caeb6629c1fee6380a773e14
2018-11-12IVGCVSW-2125 : Consolidate backend registries into oneDavid Beck
Change-Id: I56da4780f8f5fcef7ff01d232d5d61bf299364bf
2018-11-12IVGCVSW-2054: BATCH_TO_SPACE_ND Reference implementation and Unit tests.Éanna Ó Catháin
Change-Id: I13c6728dbb60643d0e086d171225c5d802987f92
2018-11-09IVGCVSW-2082 - add SimpleConvolution2dAsymmetricPaddingNhwc to CL test after ↵narpra01
ACL fix the convolution issue. Change-Id: If72f6f4e32567bcfa4af13836e411a3199ede010
2018-11-09IVGCVSW-2125 : backends now can return optimizationsDavid Beck
Change-Id: Ieec34224b433e1d2f3bbe66632cd6016cac5498c
2018-11-09IVGCVSW-2095 Add reference implementation and unit tests for SpaceToBatchNdNattapat Chaimanowong
Change-Id: I27ffebdece6e68460931a44c15b9b029f9fce638
2018-11-08IVGCVSW-2056+IVGCVSW-2064 : move ClContextControl to the ClBackendexperimental/nhwc-previewDavid Beck
* add IBackendContext interface * add ClBackendContext implementation Change-Id: I13e4d12b73d4c7775069587675276f7cee7d630b
2018-11-08IVGCVSW-1709: Clean up memory manager bodgeAron Virginas-Tar
* Added quick workaround for the memory management errors in the CL/Neon unit tests Change-Id: I56250db462cdbdc1acc0a5824807d288fb0c1d11
2018-11-08IVGCVSW-2037 : Documenting pluggable backendsDavid Beck
also in IVGCVSW-2019 + IVGCVSW-2005 + IVGCVSW-1987 IVGCVSW-1642 Change-Id: I33809fd2f30aac248ec45f070f717b8dcf5de3cf
2018-11-07IVGCVSW-1949 : Refactor ITensorHandle and move backend specifics to their placeDavid Beck
Change-Id: I48242425c6a6856e13ebcee1b140cbd2af94a3aa
2018-11-05Revert "IVGCVSW-2056 + IVGCVSW-2064 : move ClContextControl to the ClBackend"David Beck
This reverts commit d4dfa684941a21314b70593d01b0fc2167eebad4. Change-Id: Id61ce69215505c3cf5d30ec2a7ec9127fb2554fc
2018-11-05IVGCVSW-2113: Update ClDepthWiseConvolutionWOrkload to suit NCHW/NHWC ↵saoste01
DataLayout (3*3 Optimization) Change-Id: Icfc137201c52e2c856076b7795572cc4ba75cc95
2018-11-02IVGCVSW-1946: Remove armnn/src from the include pathsAron Virginas-Tar
Change-Id: I663a0a0fccb43ee960ec070121a59df9db0bb04e
2018-11-02IVGCVSW-2093 Add SpaceToBatchNd layer and corresponding no-op factory ↵Nattapat Chaimanowong
implementations Change-Id: Ibd457f3a2d4342c4d6335bd3c471282a14ab6b14
2018-11-01IVGCVSW-2103: Add 2-Channel unit tests ResizeBilinearJames Conroy
* Modifies ResizeBilinear unit tests to use 2-Channel tensor shapes for input and output data, to improve test coverage when exercising NHWC data layout. * Refactors unit tests to permute input and output data when exercising NHWC data layout. Change-Id: Ib7fb438cac23e78ff0104c895c3b7596bf7c3aa7
2018-11-01IVGCVSW-2074: Updated the DepthwiseConvolution2dDepthMul1 for NHWCjimfly01
Change-Id: Ibaa0b909680a6f2a155e4ca6fa24e1144d6e6e73
2018-11-01IVGCVSW-2074: Updated CompareDepthwiseConvolution2dTest for NHWCjimfly01
Change-Id: Ib0568024b4f43ae17e6c75ac35d31cf103ce3482
2018-10-31IVGCVSW-1970 TfLite VGG16: Use same number of iterations as other testsMatthew Bentham
I had forgotten that as a workaround for the testing using a different number of test cases for different hardware backends, we repeat the expected test results an arbitrary number of times Change-Id: I4d1ea8daa1cbfd63ebcd7ac93ac30acb5806fafe
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
2018-10-30IVGCVSW-2074: Updated the DepthwiseConvolution2dTest for NHWCjimfly01
Change-Id: If2befd3bd75da70c57f924cbe18fa0a47bf7a27f
2018-10-30IVGCVSW-1970 TfLite VGG16: Correct number of iterationsMatthew Bentham
Change-Id: Iaf03755b0d30598f5d09ca36af8eeeb369191950
2018-10-30IVGCVSW-1970 TfLite VGG16: Add Validation.txt for continuous integrationMatthew Bentham
Change-Id: Ib7ea0a0b809bdfe1d705b31a08f42e1b7815b0d2
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
generated by cgit v1.2.1 (git 2.23.0) at 2024-07-04 12:46:45 +0000