aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2018-11-28IVGCVSW-2205 Fixed a bug in DepthWiseConv workload where NCHW layout was assumedbranches/armnn_18_11Mohamed Nour Abouelseoud
Includes a temporary workaround for COMPMID-1813 Change-Id: I3e5217281be072d5b61788ab8a75e818bbc5d247 (cherry picked from commit 7e7261ed9a4f8d48c86e57044312e3df82189713 on master)
2018-11-26IVGCVSW-2199 Call Resize only if H and/or W changesJames Conroy
* Wrap Resize function call with conditional checking if height and/or width need to be changed. Change-Id: Ic33c3ed29cc985c147d29db8e9dd237ab9c741d1 (cherry picked from commit e02d60154d8230f555c832c1cce1865b54dc6589)
2018-11-26IVGCVSW-2141 BuildGuideCrossCompilation.md Documentation updatesurmeh01
* Removed the usage of g++-5 as we can build it using later versions Change-Id: I073c84868c8619aeb5e4bd3006b87d10b7fec37e
2018-11-23IVGCVSW-2183 BuildGuideCrossCompilation.md Documentation updateFrancisMurtagh
* Removed confusing mention of Anaconda and CuDNN and reworded Change-Id: I2e4d86704c6564b2d18cec191246edd15cde0905 (cherry picked from commit 0e76ed0a6ab74be72a27121747ce78a516872c53)
2018-11-22IVGCVSW-2135: Update Readme to include links to new ONNX and TensorFlow Lite ↵Brian Joyce
guides Change-Id: Ia040a6accb4ae07156b2e1ad0ebef12423f647ed
2018-11-20IVGCVSW-2117 - BuildGuideCrossCompilation.md Documentation updateFrancisMurtagh
* Updated build guide to include instruction to copy libprotobuf.so.15 into the build folder before moving to arm64 machine. Change-Id: Ia20691edc79ff59fa4147eafbbfd3997b2531317
2018-11-20IVGCVSW-2144: Adding TensorUtils classNina Drozd
* helper methods for creating TensorShape and TensorInfo objects Change-Id: I371fc7aea08ca6bbb9c205a143ce36e8353a1c48
2018-11-20IVGCVSW-2175 - Add support for uint8 Concatenation on CLnarpra01
Change-Id: I9bc46e17e11d73ee1a3bc4f9ec07d46be77fcbcb
2018-11-20MLCE-64: Updating BuildGuideAndroidNDK.md for Ubuntu 18.04saoste01
Change-Id: Iab9c4952f5478d4805dba56e838f9c33d2b598ee
2018-11-20IVGCVSW-2043 Merger using ACL for innermost concat axisMatteo Martincigh
* Fixed unsigned to signed conversion error that was breaking master Change-Id: I08d79d9bf131eb46ea0495371160698ab59c1721
2018-11-19IVGCVSW-2115: Fix for unset USERNAMEjimfly01
* When running the script standalone USERNAME can be unset causing failure Change-Id: Idb1752117c319c8946426efe8882f03034b2bbbf
2018-11-19IVGCVSW-2169 Remove DataLayoutIndexed from public APIMatthew Bentham
Change-Id: If8d8087d9d365e467d3ca9bf9c40d7219cb75cfd
2018-11-19IVGCVSW-2105 - Unit tests for mergernarpra01
* Add LayerTests * Add WorkloadTests !android-nn-driver:166 Change-Id: I903461002879f60fc9f8ae929f18784e2d9b1fc1
2018-11-19IVGCVSW-2168: Remove DataLayout from LayerAron Virginas-Tar
Change-Id: Iab6ad04e5c786e4e639578f7b1d1537dd1196e2f
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
generated by cgit v1.2.1 (git 2.23.0) at 2024-05-03 22:24:24 +0000