Age | Commit message (Collapse) | Author |
|
* Compute Softmax Acl axis for Cl and Neon
* Add unittests for Softmax in 3D and 4D
* Correct input and output layer names in CaffeSqueezeNet inference test
Change-Id: I2d369d9a2db19c40f2af3341039dd33f0c5637b1
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
|
|
* Update Neon Subtraction/Multiplication to use BaseWorkload
* Add Uint8 tests for Subtraction/Multiplication
Change-Id: Ied2aa048924817a4db0025b9bd9e54151667bd74
Signed-off-by: Conor Kennedy <conor.kennedy@arm.com>
|
|
* Add uint8 tests
Change-Id: I178e34a638411fa065bdc4c722136a02ba9e000b
Signed-off-by: Conor Kennedy <conor.kennedy@arm.com>
|
|
no longer work
* Added two master variables ARMNN_COMPUTE_CL_ENABLED and ARMNN_COMPUTE_NEON_ENABLED
to android-nn-driver/Android.mk to easily control backend support
* Setting either of those two new variables then properly sets the
corresponding build macro
* If a specific backend gets disabled, the corresponding source files
will be excluded from the build
* Unified the usage of the pre-compile macros
!android-nn-driver:613
Change-Id: I582ff73493b70ba9e22ca2e38d875a0f19566c8a
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
|
|
Change-Id: I3e971c66798610d2c96445fa3babb7cc90cf8031
Signed-off-by: Éanna Ó Catháin <eanna.ocathain@arm.com>
|
|
subgraphs are optimized by the backends
* Added a new method OptimizeSubGraph to the backend interface
* Refactored the Optimize function so that the backend-specific
optimization is performed by the backend itself (through the new
OptimizeSubGraph interface method)
* Added a new ApplyBackendOptimizations function to apply the new
changes
* Added some new convenient constructors to the SubGraph class
* Added AddLayer method and a pointer to the parent graph to the
SubGraph class
* Updated the sub-graph unit tests to match the changes
* Added SelectSubGraphs and ReplaceSubGraphConnections overloads
that work with sub-graphs
* Removed unused code and minor refactoring where necessary
Change-Id: I46181794c6a9e3b10558944f804e06a8f693a6d0
|
|
Change-Id: Ic165061cc61534e7e391a398ea7c2918240e2d3b
|
|
Change-Id: I0d949a9f23a61af5013efdd18572b29fae585f2a
|
|
Change-Id: I0d14baf9002c894790da171a6d60c0e4ac929078
|
|
* Added DetectionPostProcessQueueDescriptor to WorkloadData
* Added CreateDetectionPostProcess function in WorkloadFactory.hpp
* Added stub implementation of the CreateDetectionPostProcess
in workload factories
* Added DetectionPostProcessLayer stub implementation
* Added AddDetectionPostProcessLayer to Network
* Added IsDetectionPostProcessSupported to LayerSupportBase
Change-Id: Ifc071b3b6b12877c997bdcc43d769c8f891d5c6c
|
|
* Remove Equal and Greater from RefElementwiseWorkload
* Create RefComparisonWorkload and add Equal and Greater
* Update ElementwiseFunction for different input/output types
* Update TfParser to create Equal/Greater with Boolean output
* Update relevant tests to check for Boolean comparison
Change-Id: I299b7f2121769c960ac0c6139764a5f3c89c9c32
|
|
* Add end to end test for Gather operator
* Add Support for int32 to Constant layer for Ref
* Add Int32Workload
* Add RefConstantWorkload as template for float, uint8, int32
* Remove unused RefBaseConstantWorkload
* Remove unused RefConstantFloat32Workload
* Remove unused RefConstantUint8Workload
* Add support check for int32 in LayerSupport functions
Change-Id: Ic970588a49ebe2aafb12be8adef52371feacaa7b
|
|
* Implemented NeonResizeBilinearWorkload
* Enable ResizeBilinear Operator unit tests for Neon
!android-nn-driver:405
Change-Id: Iec3100ccaf7d246e8eaf683d1f3ec9191df5241e
|
|
* Refactored all the workload factories to use "virtual" properly
* Removed the precompiled layer support from the optimizer
* Disabled compiler optimization for debug build to ease debugging
Change-Id: I6ab83abd78f422771359295e25b79bb9be613cfd
|
|
Change-Id: I7359617a307b9abb4c30b3d5f2364dc6d0f828f0
|
|
* Added GatherQueueDescriptor to WorkloadData
* Added CreateGather function in WorkloadFactory.hpp
* Added stub implementation of the CreateGreater function in workload factories
* Added GatherLayer stub implementation
* Added AddGatherLayer to Network
* Added IsGatherSupported to LayerSupportBase
Change-Id: I0408fd54e88a7d4e3d9e1c2811a9323f0da52a04
|
|
separate branch) and master
* Brings in all the changes done for the pluggable backends
* Added sub-graph support and tests
* Added precompiled layer support and tests
* Moved BackendSettings to a separate file
* Removed the backend-specific code
* Ported DebugLayer and associated functionality
* Included fixes to make those changes work with master
Change-Id: Id7028fa7917527b844628d5aff5732e3d94c0488
|
|
code base
* Made the virtual functions in ILayerSupport.hpp pure
* Created a LayerSupportBase class with the default implementation of
the interface
* Made the backend layer support classes inherit from the base
class, instead of directly from the interface
* Refactored the profiler and the profiling event classes to use
the BackendId instead of the Compute
* Implemented a proper MemCopy support method
* Changed Compute to BackendId in the profiling API and objects
* Removed static references to pluggable backends
!android-nn-driver:492
Change-Id: Id6332b5f48c980819e0a09adc818d1effd057296
|
|
Change-Id: I43be451f490db0154021f47a2fd49d1269cf5b95
|
|
Change-Id: I0bc48f118aba419abb659657b83224401fac0715
|
|
Just include the function definition that is specifically needed for each workload.
Also, tighten up the scope where Compute Library functions are available.
Knocks about 30seconds off a 4m30s single-threaded compile of the Neon workloads.
Change-Id: Idac438f3bc77ff978295fbc9505cb42447def145
|
|
*Added Unit Tests
Change-Id: I6cceb8e6dcda35ce08415f8e5ca86019a64d26e3
|
|
* Unified ArmNN's weight format to [ M, I, H, W ] for the depthwise convolution
* Added conversion utilities to permute/reshape the weights as appropriate
when using CL and Neon backends
* Updated the reference implementation of the convolution
* Updated the relevant unit tests accordingly
!android-nn-driver:459
Change-Id: I07d0818efa9d1ca1e5dad82983aac1fe78eadb18
|
|
default cases are handled by DefaultLayerSupport
Change-Id: I31942a5e8515d6fdce9a0adf20906eaabc2b9aa6
|
|
Change-Id: Icf7ef88a2eaef80ec32cc718b0ca9d26e830ed07
|
|
Change-Id: Iae6a3bfad06cb669ef0abea465d03163bb8316f5
|
|
Factor out new BuildArmComputeReductionCoordinates function
from CL backend into ArmComputeTensorUtils.
Update NEON LayerSupport and WorkloadFactory objects
Change-Id: Icc975ec699199bffafbdb207323df509d35e1e04
|
|
Technical debt work towards adding some new Neon workloads
Change-Id: I08ab6dd14d0e89d4ebc8a878fb69caa5681012bf
|
|
Change-Id: Iddae3486641d2d195827ae4e0a9dfa3f7ccd65e3
|
|
* Added the Greater operation as an element-wise workload
* Added the unit tests
Change-Id: Ie00ee30e47a5f5e17a728032eeb11a085d06c8f2
|
|
* Add reference equal workload
* Add Reference Workload Unit Test
Change-Id: If2848e7dde4248566b99d91726d08143c40ff80d
|
|
Equal operation
* Add QueueDescriptor in WorkloadData.hpp
* Add CreateEqual function in WorkloadFactory.hpp
* Added stub implementation of the CreateEqual function in RefWorkloadFactory,
NeonWorkloadFactory and ClWorkloadFactory
Change-Id: Iec6dc2f989c67fa6f0c32cfb93508995c8580783
|
|
per COMPMID-1818 change to using Blob-based memory manager.
Will change back when COMPMID-1848 is fixed.
Change-Id: I6e22c2edf422202410faa717b330a2c96c3ebbe5
|
|
Greater operation
* Added QueueDescriptor in WorkloadData.hpp
* Added CreateGreater function in WorkloadFactory.hpp
* Added stub implementation of the CreateGreater function in RefWorkloadFactory,
NeonWorkloadFactory and ClWorkloadFactory
* Added GreaterLayer stub implementation
* Renamed ArithmeticBaseLayer to ElementwiseBaseLayer
Change-Id: I7e38c2936de905da921a92ba3f918478169ec7f5
|
|
Kernel position within the layer is part of the kernel name
Change-Id: I3b9ee870fbd0db025f1515c81245f917189ae884
|
|
Change-Id: I0d69a72df9e348cbeca690926485c050499d1051
|
|
Unit tests not yet added as need Compute Library a84faffd.
Change-Id: Ica16df493e8d6a76da9d1f74bf43b8403f9dff62
|
|
NEFillBorderKernel may not be issued for some activation workloads
depending on the version of the Compute Library.
Change-Id: I01b8960f9eb7a0192cd351eddbb416ac05248b34
|
|
* 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
|
|
Change-Id: I5455b720565248ff94278e76887d63f8434a7b58
|
|
* Changed NeonL2Normalisation to use NEL2NormalizeLayer to
normalise along the channel axis in either NCHW or NHWC format
Change-Id: Ibaf119b6a3de3c0f80f94b1c5fe9a356cf1fbd0e
|
|
Change-Id: I03fa374fd9692d98257de709f8c3ad0a49c88b95
|
|
workloads and workload functions
Change-Id: I6f3fce12a55f7d38ceafcdfcd6b5181bf56e2c09
|
|
Change-Id: I8964f5e8978c2d2a07734a381e3f7c656c22456a
|
|
Includes a temporary workaround for COMPMID-1813
Change-Id: I3e5217281be072d5b61788ab8a75e818bbc5d247
|
|
Change-Id: Icc1de9b69d7bb74b6bf5a6a6f315cf07fe2c5223
|
|
Enabled subtraction broadcasting tests for CL/NEON
Enabled Uint8 subtraction tests for CL
Change-Id: Id36c1530f967c77f5633616e8f491cac9547724b
|
|
* Add CommonTestUtils
* Add end to end layer test implementation
* Add example usage for Merger layer on Ref, Cl, Neon
Change-Id: I8931136288cd68b80bcdad8f5ae087ae1a70a60a
|
|
Change-Id: I9bc46e17e11d73ee1a3bc4f9ec07d46be77fcbcb
|
|
Change-Id: If8d8087d9d365e467d3ca9bf9c40d7219cb75cfd
|