jimfly01 [Tue, 4 Dec 2018 17:47:22 +0000 (17:47 +0000)]
IVGCVSW-2333 Add ParseSub method to TfParser
* Also added unit test Sub.cpp
Change-Id: I6d23c11ae894ee433cd28ffdf0248b14e01b0131
jimfly01 [Thu, 6 Dec 2018 16:19:52 +0000 (16:19 +0000)]
IVGCVSW-2275 Remove swizzling from ParseResizeBilinear
Change-Id: I0d02faf188f441f017967057f16f4661d321978a
FrancisMurtagh [Thu, 6 Dec 2018 15:26:04 +0000 (15:26 +0000)]
IVGCVSW-2277 Remove the input swizzling from ParsePooling2d
* Remove input swizzling from ParsePooling2D and add parameterized
tests for NCHW, NHWC and Padding="SAME".
Change-Id: I4786fcc31b6ac46bf19d887f007963eb924f0f9f
Mohamed Nour Abouelseoud [Thu, 6 Dec 2018 14:29:25 +0000 (14:29 +0000)]
Removed square kernel in range validation in CaffeParser
as validation assumptions should not be made and
should be handled by the backend
Change-Id: I1565daeb0abfdc0bb01981eab2a1937a5af7976e
Matteo Martincigh [Thu, 6 Dec 2018 09:06:29 +0000 (09:06 +0000)]
IVGCVSW-2193 ExpandDims operation implementation
* Fix for a signedness error in Android 32 builds
Change-Id: Id909ee2d50f376782de3b80aaef503e08f6d1268
Nattapat Chaimanowong [Wed, 5 Dec 2018 15:17:18 +0000 (15:17 +0000)]
IVGCVSW-2315 Add descriptor for Debug
Change-Id: I6b26c681989ef815752186f027a245ef8da7aea2
ruoyan01 [Tue, 4 Dec 2018 18:24:08 +0000 (18:24 +0000)]
IVGCVSW-2276: Remove the input swizzling in ParseLrn
Change-Id: If5ef3dc426bd6fa5aab342dcece6e99f86e65dba
Matteo Martincigh [Wed, 5 Dec 2018 13:10:45 +0000 (13:10 +0000)]
IVGCVSW-2267 Remove the input swizzling from ParseFusedBatchNorm
* Removed the input swizzling when the data layout is NHWC
* Split the unit test into NHWC and NCHW cases
Change-Id: I6b9fef70bc4ba5e01d14cbfaea3c842a289b0a0e
Matteo Martincigh [Wed, 28 Nov 2018 16:22:36 +0000 (16:22 +0000)]
IVGCVSW-2264 Remove input swizzling from ParseConv2D in the TF parser
* 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
Conor Kennedy [Wed, 5 Dec 2018 11:05:54 +0000 (11:05 +0000)]
IVGCVSW-2193 ExpandDims operation implementation
* Add ExpandDims operation to TfParser.cpp
Change-Id: Ifa756ae0667c11e3b6daec8f6dd4e54cac88d16a
jimfly01 [Tue, 4 Dec 2018 10:09:52 +0000 (10:09 +0000)]
IVGCVSW-2296 Add ParsePad method to TfParser
* 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
Matteo Martincigh [Wed, 28 Nov 2018 16:22:22 +0000 (16:22 +0000)]
IVGCVSW-2264 Move DataLayoutIndexed to armnnUtils
* 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
Nattapat Chaimanowong [Tue, 4 Dec 2018 13:47:02 +0000 (13:47 +0000)]
IVGCVSW-2251 Add support for Minimum operator in TfParser
Change-Id: Ib84e5bde39d706c5125e0f84577195fc61107a4a
Éanna Ó Catháin [Tue, 4 Dec 2018 10:29:06 +0000 (10:29 +0000)]
IVGCVSW-2247 Adding a min Elementwise Workload and tests
Change-Id: I017ca6c23b62a8978982de0ca4ad204cb8cf7c67
Sadik Armagan [Tue, 4 Dec 2018 10:02:08 +0000 (10:02 +0000)]
IVGCVSW-2256 Add parser function in TensorFlow Parser (Maximum)
* Extended Maximum operator support in TF Parser
* Added extra unit tests for Maximum operator in TF Parser
Change-Id: I68edb43b2a3105507f2f5f028ff0e35206965dca
Nattapat Chaimanowong [Mon, 3 Dec 2018 16:06:49 +0000 (16:06 +0000)]
IVGCVSW-2315 Add DebugLayer and no-op factory method
Change-Id: I5455b720565248ff94278e76887d63f8434a7b58
Éanna Ó Catháin [Mon, 3 Dec 2018 13:04:22 +0000 (13:04 +0000)]
IVGCVSW-2255 Add unit test for maximum reference workload
* Enable Maximum workload
Change-Id: I5f7786ff66f135f0c74935dbf5861e5a4239bcc8
FrancisMurtagh [Thu, 29 Nov 2018 17:13:36 +0000 (17:13 +0000)]
IVGCVSW-2118 L2Normalization ACL function used for Neon
* Changed NeonL2Normalisation to use NEL2NormalizeLayer to
normalise along the channel axis in either NCHW or NHWC format
Change-Id: Ibaf119b6a3de3c0f80f94b1c5fe9a356cf1fbd0e
FrancisMurtagh [Fri, 30 Nov 2018 17:18:55 +0000 (17:18 +0000)]
IVGCVSW-2312 Update CL pin to include their L2Normalization Neon changes
* Updated Revision number in the get_compute_library.sh to after the
implementation of COMPMID-1645 NEL2Normalization for FP32/FP16 & NHWC
Change-Id: Id9f437e833aafdb83c76bec1ba3fe79fdbab1a69
saoste01 [Wed, 28 Nov 2018 16:57:20 +0000 (16:57 +0000)]
IVGCVSW-2254 Add Reference workload for Maximum
Change-Id: Id7302c6b1df995ebe6eb8eb94bab38bee1b31b0b
kevmay01 [Thu, 29 Nov 2018 08:40:19 +0000 (08:40 +0000)]
IVGCVSW-2245 Add Minimum Layer and no-op Factory implementation
Change-Id: I03fa374fd9692d98257de709f8c3ad0a49c88b95
Éanna Ó Catháin [Wed, 28 Nov 2018 16:24:38 +0000 (16:24 +0000)]
IVGCVSW-2202 Refactoring Arithmetic* names to Elementwise* names for workloads and workload functions
Change-Id: I6f3fce12a55f7d38ceafcdfcd6b5181bf56e2c09
Nattapat Chaimanowong [Wed, 28 Nov 2018 10:44:37 +0000 (10:44 +0000)]
IVGCVSW-2253 Add maximum layer and corresponding no-op factory implementation
Change-Id: I8964f5e8978c2d2a07734a381e3f7c656c22456a
Mike Kelly [Wed, 28 Nov 2018 11:52:08 +0000 (11:52 +0000)]
IVGCVSW-1199: BATCH_TO_SPACE_ND integrate Arm Compute CL
Change-Id: Ic772acf481caed6e8a6b99f68a63dfc2a34c24dc
Mohamed Nour Abouelseoud [Tue, 27 Nov 2018 17:35:35 +0000 (17:35 +0000)]
IVGCVSW-2205 Fixed a bug in DepthWiseConv workload where NCHW layout was assumed
Includes a temporary workaround for COMPMID-1813
Change-Id: I3e5217281be072d5b61788ab8a75e818bbc5d247
Nattapat Chaimanowong [Fri, 23 Nov 2018 15:33:41 +0000 (15:33 +0000)]
IVGCVSW-2087 Reference implementation and unit tests for StridedSlice
Change-Id: Ifeacc0adb4547c72537b9ea7a61bf3c4ec3673fa
Rob Hughes [Wed, 21 Nov 2018 13:34:24 +0000 (13:34 +0000)]
Fix documentation for depthwise convolution
Change-Id: Ib2bf543fc4f855da94eb1d34a91637f7868321cd
Rob Hughes [Wed, 21 Nov 2018 09:55:52 +0000 (09:55 +0000)]
Fix compile errors on Windows
Change-Id: I40acb42360bfcda09485efb2a54144d8e35bdafb
James Conroy [Mon, 26 Nov 2018 09:48:30 +0000 (09:48 +0000)]
IVGCVSW-2199 Call Resize only if H and/or W changes
* Wrap Resize function call with conditional checking
if height and/or width need to be changed.
Change-Id: Ic33c3ed29cc985c147d29db8e9dd237ab9c741d1
surmeh01 [Fri, 23 Nov 2018 14:10:54 +0000 (14:10 +0000)]
IVGCVSW-2141 BuildGuideCrossCompilation.md Documentation update
* Removed the usage of g++-5 as we can build it using later versions
Change-Id: I073c84868c8619aeb5e4bd3006b87d10b7fec37e
FrancisMurtagh [Wed, 21 Nov 2018 16:44:12 +0000 (16:44 +0000)]
IVGCVSW-2183 BuildGuideCrossCompilation.md Documentation update
* Removed confusing mention of Anaconda and CuDNN and reworded
Change-Id: I2e4d86704c6564b2d18cec191246edd15cde0905
Aron Virginas-Tar [Thu, 22 Nov 2018 15:04:42 +0000 (15:04 +0000)]
Refactor JSON printer test implementation
Change-Id: Icc1de9b69d7bb74b6bf5a6a6f315cf07fe2c5223
Aron Virginas-Tar [Wed, 21 Nov 2018 13:14:42 +0000 (13:14 +0000)]
Refactor inlined utility functions in NetworkUtils
Change-Id: I26fb13717f64c942b2648702c52be18be856042d
Brian Joyce [Thu, 22 Nov 2018 09:58:27 +0000 (09:58 +0000)]
IVGCVSW-2135: Update Readme to include links to new ONNX and TensorFlow Lite guides
Change-Id: Ia040a6accb4ae07156b2e1ad0ebef12423f647ed
Nattapat Chaimanowong [Wed, 21 Nov 2018 16:48:17 +0000 (16:48 +0000)]
IVGCVSW-2086 Update StridedSliceLayer and StridedSliceDescriptor
Change-Id: Ifa88a879dd239f60ab27330d6b73859393828ef0
Mohamed Nour Abouelseoud [Wed, 21 Nov 2018 10:35:17 +0000 (10:35 +0000)]
IVGCVSW-1837: Enable broadcast tests for SUB CL/NEON Workload
Enabled subtraction broadcasting tests for CL/NEON
Enabled Uint8 subtraction tests for CL
Change-Id: Id36c1530f967c77f5633616e8f491cac9547724b
David Beck [Tue, 20 Nov 2018 16:52:31 +0000 (16:52 +0000)]
Remove leftover header from backendsCommon test
Change-Id: I3a6077ad9ded9002aea9c888daab68b6452bd235
Matteo Martincigh [Tue, 20 Nov 2018 16:40:24 +0000 (16:40 +0000)]
Updated the CL pin to take in the fix for CLBatchToSpace
Change-Id: I2d5f017917b1c773ff3da96ab28de415c1e77c0d
narpra01 [Tue, 20 Nov 2018 15:21:28 +0000 (15:21 +0000)]
IVGCVSW-2173 - Add end to end layer test implementation and example usage
* Add CommonTestUtils
* Add end to end layer test implementation
* Add example usage for Merger layer on Ref, Cl, Neon
Change-Id: I8931136288cd68b80bcdad8f5ae087ae1a70a60a
David Beck [Tue, 20 Nov 2018 13:57:09 +0000 (13:57 +0000)]
IVGCVSW-2179 : ArmNN Contirbutor Guide
Change-Id: I4887e3509a7f406c80f7eb55c04bdf62395c6cf6
Matthew Bentham [Tue, 20 Nov 2018 14:33:33 +0000 (14:33 +0000)]
IVGCVSW-1199 Disable auto-flattening of Compute Library tensors
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
FrancisMurtagh [Tue, 20 Nov 2018 14:42:46 +0000 (14:42 +0000)]
IVGCVSW-2117 - BuildGuideCrossCompilation.md Documentation update
* Updated build guide to include instruction to copy
libprotobuf.so.15 into the build folder before moving
to arm64 machine.
Change-Id: Ia20691edc79ff59fa4147eafbbfd3997b2531317
Aron Virginas-Tar [Tue, 20 Nov 2018 14:31:13 +0000 (14:31 +0000)]
Minor improvements and changes in backends/README.md
Change-Id: I55e27c50953c5e3f0b43bcd7aa8643015480181d
Nina Drozd [Mon, 19 Nov 2018 13:03:36 +0000 (13:03 +0000)]
IVGCVSW-2144: Adding TensorUtils class
* helper methods for creating TensorShape and TensorInfo objects
Change-Id: I371fc7aea08ca6bbb9c205a143ce36e8353a1c48
narpra01 [Tue, 20 Nov 2018 11:29:12 +0000 (11:29 +0000)]
IVGCVSW-2175 - Add support for uint8 Concatenation on CL
Change-Id: I9bc46e17e11d73ee1a3bc4f9ec07d46be77fcbcb
saoste01 [Mon, 19 Nov 2018 19:41:52 +0000 (19:41 +0000)]
MLCE-64: Updating BuildGuideAndroidNDK.md for Ubuntu 18.04
Change-Id: Iab9c4952f5478d4805dba56e838f9c33d2b598ee
Matteo Martincigh [Tue, 20 Nov 2018 09:34:27 +0000 (09:34 +0000)]
IVGCVSW-2043 Merger using ACL for innermost concat axis
* Fixed unsigned to signed conversion error that was
breaking master
Change-Id: I08d79d9bf131eb46ea0495371160698ab59c1721
jimfly01 [Mon, 19 Nov 2018 13:42:45 +0000 (13:42 +0000)]
IVGCVSW-2115: Fix for unset USERNAME
* When running the script standalone USERNAME can be unset causing failure
Change-Id: Idb1752117c319c8946426efe8882f03034b2bbbf
Matthew Bentham [Mon, 19 Nov 2018 13:19:28 +0000 (13:19 +0000)]
IVGCVSW-2169 Remove DataLayoutIndexed from public API
Change-Id: If8d8087d9d365e467d3ca9bf9c40d7219cb75cfd
narpra01 [Mon, 19 Nov 2018 15:30:27 +0000 (15:30 +0000)]
IVGCVSW-2105 - Unit tests for merger
* Add LayerTests
* Add WorkloadTests
!android-nn-driver:166
Change-Id: I903461002879f60fc9f8ae929f18784e2d9b1fc1
Aron Virginas-Tar [Mon, 19 Nov 2018 13:06:49 +0000 (13:06 +0000)]
IVGCVSW-2168: Remove DataLayout from Layer
Change-Id: Iab6ad04e5c786e4e639578f7b1d1537dd1196e2f
Nikhil Raj [Mon, 19 Nov 2018 14:51:07 +0000 (14:51 +0000)]
IVGCVSW-2043 - Merger using ACL for innermost concat axis
* 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
Aron Virginas-Tar [Mon, 19 Nov 2018 10:58:30 +0000 (10:58 +0000)]
IVGCVSW-2167: Run parser unit tests on the reference backend only
Change-Id: Ib11c3d36c7109198da7266955414580e8fb916b5
Matthew Bentham [Mon, 19 Nov 2018 11:28:58 +0000 (11:28 +0000)]
Fix for Github issue #103
Use CMAKE_THREAD_LIBS_INIT instead of pthread in sample_app.
The separate pthread library doesn't exist on Android.
Change-Id: I9a363ba7d29d2673359349f5f4288844f0550946
Matteo Martincigh [Mon, 19 Nov 2018 09:39:16 +0000 (09:39 +0000)]
Changed the mode of generate_tensorflow_protobuf.sh to executable
Change-Id: I0042395b46906f70d09a16b4122af3d911f5a53d
jimfly01 [Mon, 19 Nov 2018 11:00:42 +0000 (11:00 +0000)]
IVGCVSW-2115: Updated README.md
* Added line to README.md explaining the function of the get_compute_library.sh script
Change-Id: If6be1c64443dcd6d0a08a12485de3d38614542f0
jimfly01 [Thu, 15 Nov 2018 15:46:11 +0000 (15:46 +0000)]
IVGCVSW-2115: Script to clone/fetch correct clframework
* 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
narpra01 [Fri, 16 Nov 2018 12:38:41 +0000 (12:38 +0000)]
IVGCVSW-2155 - Always call NEConvolutionLayer in NeonConvolution2dWorkload
* Remove check for preferDirectConvolution
* Remove IsNeonDirectConvolutionPreferred
* Remove unused tests and functions
Change-Id: I3f0868f41403ec5fa740889e7bdcb4415ad77bda
FrancisMurtagh [Fri, 16 Nov 2018 12:26:20 +0000 (12:26 +0000)]
IVGCVSW-2017: CLWorkload to use L2Normalization
* Changed ClL2Normalisation from using CLNormalizationLayer
to use CLL2NormalizeLayer to normalise along the channel axis
in either NCHW or NHWC format.
Change-Id: I399cbee408a277d1ef8c6c85ebcbd86d6c3e407b
Ferran Balaguer [Fri, 16 Nov 2018 11:56:01 +0000 (11:56 +0000)]
IVGCVSW-2158 BuildGuideCrossCompilation.md wrong protobuf version
Change-Id: Ibe826db4412c54aba42c45c155e7e5329861bdb1
Aron Virginas-Tar [Fri, 16 Nov 2018 11:00:48 +0000 (11:00 +0000)]
IVGCVSW-2162: Remove conditional compilation directives from ArmComputeUtils
Change-Id: Ie2f134fd51de919c50fa9d8d82bbb4ed4ee46469
Aron Virginas-Tar [Fri, 16 Nov 2018 10:26:23 +0000 (10:26 +0000)]
IVGCVSW-2157: Remove conditional compilation directives from ClBackendContext
Change-Id: I0b9818c3bc09101aa6563ea8e4a886483d3b09d1
Matteo Martincigh [Wed, 14 Nov 2018 12:39:55 +0000 (12:39 +0000)]
IVGCVSW-2092 Port LSTMCell::Eval to ArmNN
* 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
Aron Virginas-Tar [Thu, 15 Nov 2018 17:44:36 +0000 (17:44 +0000)]
IVGCVSW-2156: Remove conditional compilation directives from ClContextControl
Change-Id: I812d09a869fe7c45ce71108fb675f3e2d974e2d9
keidav01 [Thu, 15 Nov 2018 14:43:23 +0000 (14:43 +0000)]
IVGCVSW-2134: Updating version number to 18.11
Change-Id: I7cbfd5a6ab0746e0351b64a45617ed089992c1a9
Matteo Martincigh [Thu, 15 Nov 2018 10:54:54 +0000 (10:54 +0000)]
Adedd load/unload warm-up before the memory lek test to put the runtime into a
stable test (memory-wise)
This prevents false-positives when running the tests on Master
Change-Id: I4348378f3689cb3ec98686a93315d2b88bb7bcc7
Conor Kennedy [Wed, 14 Nov 2018 15:28:28 +0000 (15:28 +0000)]
IVGCVSW-2086: Add StridedSlice layer & corresponding no-op factory implementations
Change-Id: I906dcb8b4c9b491bf3a661f208c09d0ea1c0fa35
Aron Virginas-Tar [Wed, 14 Nov 2018 18:35:18 +0000 (18:35 +0000)]
IVGCVSW-2136: Remove memory management methods from workload factories
Change-Id: Idc0f94590566ac362f7e1d1999361d025cc2f67a
David Beck [Wed, 14 Nov 2018 11:33:30 +0000 (11:33 +0000)]
IVGCVSW-2064 + IVGCVSW-2066 + IVGCVSW-2125 + IVGCVSW-2128 backend docs update
Change-Id: Iccc1272e59bd71c59f810a54d6d3742859789212
Matteo Martincigh [Wed, 14 Nov 2018 15:34:14 +0000 (15:34 +0000)]
Fixed minor typos in BuildGuideCrossCompilation.md
Change-Id: I4d02a6cca8e99d70a389ca3b0ce47fb7f15ed21f
jimfly01 [Wed, 14 Nov 2018 17:47:22 +0000 (17:47 +0000)]
IVGCVSW-2152: Convert TfLiteParser to NHWC
* 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
jimfly01 [Wed, 14 Nov 2018 14:52:40 +0000 (14:52 +0000)]
IVGCVSW-2125 : Consolidate backend registries into one
* adding missing include <functional> into BackendRegistry.hpp
Change-Id: I7a4ba867a856c90a3099a782ff41b8a5fb9a9efb
Éanna Ó Catháin [Wed, 14 Nov 2018 11:26:23 +0000 (11:26 +0000)]
IVGCVSW-2054: Fixing issue with InferOutputShape implementation in BatchToSpaceNdLayer.
* added Unit test
Change-Id: I80f55e8c7afb39d96006c8dd027fc9683ea8182e
jimfly01 [Mon, 12 Nov 2018 13:32:08 +0000 (13:32 +0000)]
IVGCVSW-2017: Refactored L2Normalisation Tests
* L2Normalisation Tests now take the layout as an argument.
Change-Id: Ib393889eedb3a81c9a500da91593e90a18549c33
Aron Virginas-Tar [Mon, 12 Nov 2018 18:10:43 +0000 (18:10 +0000)]
IVGCVSW-2066: Add IMemoryManager and integrate into the backends framework
Change-Id: I93223c8678165cbc3d39f461c36bb8610dc81c05
Éanna Ó Catháin [Mon, 12 Nov 2018 17:14:43 +0000 (17:14 +0000)]
Tidying up multiple issues
* 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
David Beck [Mon, 12 Nov 2018 14:59:37 +0000 (14:59 +0000)]
IVGCVSW-2125 : Consolidate backend registries into one
Change-Id: I56da4780f8f5fcef7ff01d232d5d61bf299364bf
Éanna Ó Catháin [Mon, 12 Nov 2018 11:36:34 +0000 (11:36 +0000)]
IVGCVSW-2054: BATCH_TO_SPACE_ND Reference implementation and Unit tests.
Change-Id: I13c6728dbb60643d0e086d171225c5d802987f92
narpra01 [Fri, 9 Nov 2018 09:27:31 +0000 (09:27 +0000)]
IVGCVSW-2082 - add SimpleConvolution2dAsymmetricPaddingNhwc to CL test after ACL fix the convolution issue.
Change-Id: If72f6f4e32567bcfa4af13836e411a3199ede010
David Beck [Fri, 9 Nov 2018 14:46:40 +0000 (14:46 +0000)]
IVGCVSW-2125 : backends now can return optimizations
Change-Id: Ieec34224b433e1d2f3bbe66632cd6016cac5498c
Nattapat Chaimanowong [Fri, 9 Nov 2018 14:10:38 +0000 (14:10 +0000)]
IVGCVSW-2095 Add reference implementation and unit tests for SpaceToBatchNd
Change-Id: I27ffebdece6e68460931a44c15b9b029f9fce638
David Beck [Thu, 8 Nov 2018 09:19:14 +0000 (09:19 +0000)]
IVGCVSW-2056+IVGCVSW-2064 : move ClContextControl to the ClBackend
* add IBackendContext interface
* add ClBackendContext implementation
Change-Id: I13e4d12b73d4c7775069587675276f7cee7d630b
Aron Virginas-Tar [Wed, 31 Oct 2018 11:04:01 +0000 (11:04 +0000)]
IVGCVSW-1709: Clean up memory manager bodge
* Added quick workaround for the memory management errors in the
CL/Neon unit tests
Change-Id: I56250db462cdbdc1acc0a5824807d288fb0c1d11
David Beck [Tue, 6 Nov 2018 13:40:29 +0000 (13:40 +0000)]
IVGCVSW-2037 : Documenting pluggable backends
also in IVGCVSW-2019 + IVGCVSW-2005 + IVGCVSW-1987 IVGCVSW-1642
Change-Id: I33809fd2f30aac248ec45f070f717b8dcf5de3cf
David Beck [Tue, 30 Oct 2018 11:38:41 +0000 (11:38 +0000)]
IVGCVSW-1949 : Refactor ITensorHandle and move backend specifics to their place
Change-Id: I48242425c6a6856e13ebcee1b140cbd2af94a3aa
David Beck [Mon, 5 Nov 2018 13:40:33 +0000 (13:40 +0000)]
Revert "IVGCVSW-2056 + IVGCVSW-2064 : move ClContextControl to the ClBackend"
This reverts commit
d4dfa684941a21314b70593d01b0fc2167eebad4.
Change-Id: Id61ce69215505c3cf5d30ec2a7ec9127fb2554fc
saoste01 [Mon, 5 Nov 2018 12:30:23 +0000 (12:30 +0000)]
IVGCVSW-2113: Update ClDepthWiseConvolutionWOrkload to suit NCHW/NHWC DataLayout (3*3 Optimization)
Change-Id: Icfc137201c52e2c856076b7795572cc4ba75cc95
Aron Virginas-Tar [Thu, 1 Nov 2018 16:15:57 +0000 (16:15 +0000)]
IVGCVSW-1946: Remove armnn/src from the include paths
Change-Id: I663a0a0fccb43ee960ec070121a59df9db0bb04e
Nattapat Chaimanowong [Fri, 2 Nov 2018 10:57:25 +0000 (10:57 +0000)]
IVGCVSW-2093 Add SpaceToBatchNd layer and corresponding no-op factory implementations
Change-Id: Ibd457f3a2d4342c4d6335bd3c471282a14ab6b14
James Conroy [Thu, 1 Nov 2018 11:33:09 +0000 (11:33 +0000)]
IVGCVSW-2103: Add 2-Channel unit tests ResizeBilinear
* 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
jimfly01 [Fri, 26 Oct 2018 15:50:13 +0000 (16:50 +0100)]
IVGCVSW-2074: Updated the DepthwiseConvolution2dDepthMul1 for NHWC
Change-Id: Ibaa0b909680a6f2a155e4ca6fa24e1144d6e6e73
jimfly01 [Wed, 31 Oct 2018 14:43:53 +0000 (14:43 +0000)]
IVGCVSW-2074: Updated CompareDepthwiseConvolution2dTest for NHWC
Change-Id: Ib0568024b4f43ae17e6c75ac35d31cf103ce3482
Matthew Bentham [Tue, 30 Oct 2018 17:33:19 +0000 (17:33 +0000)]
IVGCVSW-1970 TfLite VGG16: Use same number of iterations as other tests
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
James Conroy [Wed, 31 Oct 2018 11:47:53 +0000 (11:47 +0000)]
IVGCVSW-2102: Fix Pooling2D CpuRef indexing bug
* 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
jimfly01 [Fri, 26 Oct 2018 11:56:21 +0000 (12:56 +0100)]
IVGCVSW-2074: Updated the DepthwiseConvolution2dTest for NHWC
Change-Id: If2befd3bd75da70c57f924cbe18fa0a47bf7a27f
Matthew Bentham [Tue, 30 Oct 2018 12:39:50 +0000 (12:39 +0000)]
IVGCVSW-1970 TfLite VGG16: Correct number of iterations
Change-Id: Iaf03755b0d30598f5d09ca36af8eeeb369191950
Matthew Bentham [Tue, 30 Oct 2018 10:11:23 +0000 (10:11 +0000)]
IVGCVSW-1970 TfLite VGG16: Add Validation.txt for continuous integration
Change-Id: Ib7ea0a0b809bdfe1d705b31a08f42e1b7815b0d2
Matthew Bentham [Tue, 30 Oct 2018 09:42:07 +0000 (09:42 +0000)]
MLCE-67 Fix for Github issue 91
Remove incorrect early out from image resize
Change-Id: I58014680f5cbe43dfc6b4af66638db67c070a146
Matthew Bentham [Mon, 29 Oct 2018 17:39:49 +0000 (17:39 +0000)]
IVGCVSW-2029 Tweak results handling for batch size 2 test
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
jimfly01 [Fri, 26 Oct 2018 14:55:50 +0000 (15:55 +0100)]
IVGCVSW-2074: Updated DepthwiseConvolution2dAsymmetricTest for NHWC
Change-Id: I1bc8d2f270d4abfaa62e4843b8d96bcf462c6b09