aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2018-12-10IVGCVSW-2346 Fix test wrt NEFillBorderKernel indexMatthew Bentham
Kernel position within the layer is part of the kernel name Change-Id: I3b9ee870fbd0db025f1515c81245f917189ae884
2018-12-10IVGCVSW-2354 Remove dimension validation from softmaxMohamed Nour Abouelseoud
Change-Id: I0d69a72df9e348cbeca690926485c050499d1051
2018-12-10MLCE-79 NEON QASYMM8 Addition SupportMatthew Bentham
Unit tests not yet added as need Compute Library a84faffd. Change-Id: Ica16df493e8d6a76da9d1f74bf43b8403f9dff62
2018-12-10IVGCVSW-2346 Fix test wrt NEFillBorderKernelMatthew Bentham
NEFillBorderKernel may not be issued for some activation workloads depending on the version of the Compute Library. Change-Id: I01b8960f9eb7a0192cd351eddbb416ac05248b34
2018-12-07IVGCVSW-2268 Remove the input swizzling from ParseConcatMatteo Martincigh
* Removed the input swizzling when the concatenation dimension is 3 in ParseConcat in the TF parser * No longer using the helper ProcessConcatInputTensorInfo, where the input was being swizzled if the concatenation dimension was 3 * Added a new convenience constuctor to TensorShape that initializes a shape to all zeros given only the number of dimensions Change-Id: I82a207e41bddc5fea21a0b5a38eafa24ad75d1c2
2018-12-07IVGCVSW-836 Remove 2D validation in SoftmaxMohamed Nour Abouelseoud
Change-Id: I87c53c78dd033871dbc543550a61d2d535e752ac
2018-12-07IVGCVSW-2316 Add reference implementation and unit tests for DebugNattapat Chaimanowong
Change-Id: Ib2e5de2a057da57ef77a9f5c4367d699d4773294
2018-12-06IVGCVSW-2333 Add ParseSub method to TfParserjimfly01
* Also added unit test Sub.cpp Change-Id: I6d23c11ae894ee433cd28ffdf0248b14e01b0131
2018-12-06IVGCVSW-2275 Remove swizzling from ParseResizeBilinearjimfly01
Change-Id: I0d02faf188f441f017967057f16f4661d321978a
2018-12-06IVGCVSW-2277 Remove the input swizzling from ParsePooling2dFrancisMurtagh
* Remove input swizzling from ParsePooling2D and add parameterized tests for NCHW, NHWC and Padding="SAME". Change-Id: I4786fcc31b6ac46bf19d887f007963eb924f0f9f
2018-12-06Removed square kernel in range validation in CaffeParserMohamed Nour Abouelseoud
as validation assumptions should not be made and should be handled by the backend Change-Id: I1565daeb0abfdc0bb01981eab2a1937a5af7976e
2018-12-06IVGCVSW-2193 ExpandDims operation implementationMatteo Martincigh
* Fix for a signedness error in Android 32 builds Change-Id: Id909ee2d50f376782de3b80aaef503e08f6d1268
2018-12-06IVGCVSW-2315 Add descriptor for DebugNattapat Chaimanowong
Change-Id: I6b26c681989ef815752186f027a245ef8da7aea2
2018-12-05IVGCVSW-2276: Remove the input swizzling in ParseLrnruoyan01
Change-Id: If5ef3dc426bd6fa5aab342dcece6e99f86e65dba
2018-12-05IVGCVSW-2267 Remove the input swizzling from ParseFusedBatchNormMatteo Martincigh
* Removed the input swizzling when the data layout is NHWC * Split the unit test into NHWC and NCHW cases Change-Id: I6b9fef70bc4ba5e01d14cbfaea3c842a289b0a0e
2018-12-05IVGCVSW-2264 Remove input swizzling from ParseConv2D in the TF parserMatteo Martincigh
* Removed the input swizzling when the data layout is NHWC * Permuting weights depending on the data layout used * Added getter methods to ParsedConstTfOperation to get the tensor info and the storage memory area, needed for swizzling the weights * Added unit tests for both NHWC and NCHW data layouts Change-Id: I6543900c594417df630b2663d8551158b93b7836
2018-12-05IVGCVSW-2193 ExpandDims operation implementationConor Kennedy
* Add ExpandDims operation to TfParser.cpp Change-Id: Ifa756ae0667c11e3b6daec8f6dd4e54cac88d16a
2018-12-05IVGCVSW-2296 Add ParsePad method to TfParserjimfly01
* Also added unit test armnnTfParser/test/Pad.cpp * Added missing 'Pad' entry to GetLayerTypeAsCString(LayerType) * Fixed the RefLayerSupport.IsPadSupported, now it returns true * Small fix in Optimize. Only resolve stringstream to string once Change-Id: Ieaa1886858a48cd761ac5f30454f73e44bdd4b8f
2018-12-05IVGCVSW-2264 Move DataLayoutIndexed to armnnUtilsMatteo Martincigh
* 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
2018-12-04IVGCVSW-2251 Add support for Minimum operator in TfParserNattapat Chaimanowong
Change-Id: Ib84e5bde39d706c5125e0f84577195fc61107a4a
2018-12-04IVGCVSW-2247 Adding a min Elementwise Workload and testsÉanna Ó Catháin
Change-Id: I017ca6c23b62a8978982de0ca4ad204cb8cf7c67
2018-12-04IVGCVSW-2256 Add parser function in TensorFlow Parser (Maximum)Sadik Armagan
* Extended Maximum operator support in TF Parser * Added extra unit tests for Maximum operator in TF Parser Change-Id: I68edb43b2a3105507f2f5f028ff0e35206965dca
2018-12-03IVGCVSW-2315 Add DebugLayer and no-op factory methodNattapat Chaimanowong
Change-Id: I5455b720565248ff94278e76887d63f8434a7b58
2018-12-03IVGCVSW-2255 Add unit test for maximum reference workloadÉanna Ó Catháin
* Enable Maximum workload Change-Id: I5f7786ff66f135f0c74935dbf5861e5a4239bcc8
2018-12-03IVGCVSW-2118 L2Normalization ACL function used for NeonFrancisMurtagh
* Changed NeonL2Normalisation to use NEL2NormalizeLayer to normalise along the channel axis in either NCHW or NHWC format Change-Id: Ibaf119b6a3de3c0f80f94b1c5fe9a356cf1fbd0e
2018-11-30IVGCVSW-2312 Update CL pin to include their L2Normalization Neon changesFrancisMurtagh
* Updated Revision number in the get_compute_library.sh to after the implementation of COMPMID-1645 NEL2Normalization for FP32/FP16 & NHWC Change-Id: Id9f437e833aafdb83c76bec1ba3fe79fdbab1a69
2018-11-29IVGCVSW-2254 Add Reference workload for Maximumsaoste01
Change-Id: Id7302c6b1df995ebe6eb8eb94bab38bee1b31b0b
2018-11-29IVGCVSW-2245 Add Minimum Layer and no-op Factory implementationkevmay01
Change-Id: I03fa374fd9692d98257de709f8c3ad0a49c88b95
2018-11-28IVGCVSW-2202 Refactoring Arithmetic* names to Elementwise* names for ↵Éanna Ó Catháin
workloads and workload functions Change-Id: I6f3fce12a55f7d38ceafcdfcd6b5181bf56e2c09
2018-11-28IVGCVSW-2253 Add maximum layer and corresponding no-op factory implementationNattapat Chaimanowong
Change-Id: I8964f5e8978c2d2a07734a381e3f7c656c22456a
2018-11-28IVGCVSW-1199: BATCH_TO_SPACE_ND integrate Arm Compute CLMike Kelly
Change-Id: Ic772acf481caed6e8a6b99f68a63dfc2a34c24dc
2018-11-27IVGCVSW-2205 Fixed a bug in DepthWiseConv workload where NCHW layout was assumedMohamed Nour Abouelseoud
Includes a temporary workaround for COMPMID-1813 Change-Id: I3e5217281be072d5b61788ab8a75e818bbc5d247
2018-11-26IVGCVSW-2087 Reference implementation and unit tests for StridedSliceNattapat Chaimanowong
Change-Id: Ifeacc0adb4547c72537b9ea7a61bf3c4ec3673fa
2018-11-26Fix documentation for depthwise convolutionRob Hughes
Change-Id: Ib2bf543fc4f855da94eb1d34a91637f7868321cd
2018-11-26Fix compile errors on WindowsRob Hughes
Change-Id: I40acb42360bfcda09485efb2a54144d8e35bdafb
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
2018-11-23IVGCVSW-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
2018-11-22Refactor JSON printer test implementationAron Virginas-Tar
Change-Id: Icc1de9b69d7bb74b6bf5a6a6f315cf07fe2c5223
2018-11-22Refactor inlined utility functions in NetworkUtilsAron Virginas-Tar
Change-Id: I26fb13717f64c942b2648702c52be18be856042d
2018-11-22IVGCVSW-2135: Update Readme to include links to new ONNX and TensorFlow Lite ↵Brian Joyce
guides Change-Id: Ia040a6accb4ae07156b2e1ad0ebef12423f647ed
2018-11-21IVGCVSW-2086 Update StridedSliceLayer and StridedSliceDescriptorNattapat Chaimanowong
Change-Id: Ifa88a879dd239f60ab27330d6b73859393828ef0
2018-11-21IVGCVSW-1837: Enable broadcast tests for SUB CL/NEON WorkloadMohamed Nour Abouelseoud
Enabled subtraction broadcasting tests for CL/NEON Enabled Uint8 subtraction tests for CL Change-Id: Id36c1530f967c77f5633616e8f491cac9547724b
2018-11-20Remove leftover header from backendsCommon testDavid Beck
Change-Id: I3a6077ad9ded9002aea9c888daab68b6452bd235
2018-11-20Updated the CL pin to take in the fix for CLBatchToSpaceMatteo Martincigh
Change-Id: I2d5f017917b1c773ff3da96ab28de415c1e77c0d
2018-11-20IVGCVSW-2173 - Add end to end layer test implementation and example usagenarpra01
* Add CommonTestUtils * Add end to end layer test implementation * Add example usage for Merger layer on Ref, Cl, Neon Change-Id: I8931136288cd68b80bcdad8f5ae087ae1a70a60a
2018-11-20IVGCVSW-2179 : ArmNN Contirbutor GuideDavid Beck
Change-Id: I4887e3509a7f406c80f7eb55c04bdf62395c6cf6
2018-11-20IVGCVSW-1199 Disable auto-flattening of Compute Library tensorsMatthew Bentham
This is one of the reasons why the tests in https://review.mlplatform.org/#/c/ml/armnn/+/237/ are failing (but not the only reason). Change-Id: If485bade2a6dd013cba826cec71d748fc7747249
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
2018-11-20Minor improvements and changes in backends/README.mdAron Virginas-Tar
Change-Id: I55e27c50953c5e3f0b43bcd7aa8643015480181d
generated by cgit v1.2.1 (git 2.23.0) at 2024-07-06 06:49:53 +0000