Age | Commit message (Collapse) | Author |
|
Change-Id: Ia7c305c30c39ec0e9db447a461479be17fde250c
Signed-off-by: Nattapat Chaimanowong <nattapat.chaimanowong@arm.com>
|
|
Change-Id: Ib1a795eb129de1ec3f02807a2dff7613d7c6c28d
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
Change-Id: I76f4e7db55b0efbb1a5f7d1a32bf451e66add0c7
Signed-off-by: Nattapat Chaimanowong <nattapat.chaimanowong@arm.com>
|
|
* fixed typo in Ref Merger Workload comment
* fixed typo in ViewsDescriptor comment
* made the origins descriptor accessable in the ViewsDescriptor
(needed for serialization)
* based the unit test on the use of the splitter in the CaffeParser
Change-Id: I3e716839adb4eee5a695633377b49e7e18ec2aa9
Signed-off-by: Ferran Balaguer <ferran.balaguer@arm.com>
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
|
|
* Force generation of schema header in every build
* Also fixed typo in OriginsDescriptor comment (Descriptors.hpp)
* Added Serialize/Deserialize check on Addition Layer
* Added Serialize/Deserialize check on Floor Layer
* Added Serialize/Deserialize check on Minimum Layer
* Added Serialize/Deserialize check on Maximum Layer
* Added Serialize/Deserialize check on Multiplication Layer
* Added Serialize/Deserialize check on Division Layer
Change-Id: I1358ea4db7ca506d8bcec2ee64e1fbad6005e723
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
|
|
* Added new version of AddConvolution2dLayer, AddDepthwiseConvolution2dLayer
and AddFullyConnectedLayer with Optional<ConstTensor> biases
* Deprecated old AddConvolution2dLayer, AddDepthwiseConvolution2dLayer
and AddFullyConnectedLayer methods
* Made necessary changes to implementation functions
Change-Id: I65eddb28dc72a9c74429c331815a96c2bfdc8c51
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
|
|
* Added new argument-forwarding in-place constructor to Optional
* Added MakeOptional utility template to allow for efficient construction
of optional objects
Change-Id: Iec9067fc5c3e109a26c4cc2fe8468260637b66c5
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
|
|
* Assign output shape of MobileNet SSD to ArmNN network
* Add m_OverridenOutputShapes to TfLiteParser to set shape in GetNetworkOutputBindingInfo
* Use input quantization instead of output quantization params
* Correct data and datatype in Inference test
Change-Id: I01ac2e07ed08e8928ba0df33a4847399e1dd8394
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
|
|
* Add check for infinity and negative infinity in quantize()
* Add assert for NaN value in quantize and dequantize()
* Add unit tests for infinity and negative infinity
Change-Id: Ie60e1e15b289ccbf99df4a3281f067b82cc9f9bf
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
|
|
of dimensions
Change-Id: I3589b1e901b0f81f6bb17848046a22829f91bb9e
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
|
|
* Added parser function in TFLiteParser
* Removed custom options gating
* Added unit test
* Removed template usage in VerifyTensorInfo for DeserializeParser
Change-Id: If198654ed70060855a05f8aaed010293405bd103
Signed-off-by: keidav01 <keith.davis@arm.com>
|
|
Change-Id: I9c28b8986d10b092ddc8e9b609006b27858bf6be
Signed-off-by: Saoirse Stewart <saoirse.stewart@arm.com>
|
|
* Added VisitConstantLayer to QuantizerVisitor
* Added unit tests and refactored QuantizerTest.cpp
* Code cleanup
Change-Id: I118fd2be085fc98879c5cfaa09698a7c98ba13f0
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
|
|
Change-Id: I68cf5072aca6e3a8b3b8c57e19b6d417cd5813fc
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
|
|
DepthwiseConvolution2D and FullyConnected
Change-Id: I3048504ff699fdb266488e7c07b7262e5843d4b0
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
|
|
* Minor code cleanup and refactoring
Change-Id: I9c6390c15944686134ddf4b47839762f2bb13922
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
|
|
* Added the OverrideInputRange method to the Quantizer API
* Created OverrideInputRangeVisitor to implement the override mechanism
* Moved the quantizer utility functions to the new NetworkQuantizerUtils files
* Moved the map of quantization ranges out of the StaticRangeVisitor
and into the NetworkQuantizer
* Added unit tests
* Code refactoring and cleanup
Change-Id: I9c1d006c1b6a35fbc04584a832fbe489f8f9276d
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
|
|
* end to end tests for Detection PostProcess float and uint8
* add anchors to AddDetectionPostProcessLayer
* add anchors to VisitDetectionPostProcessLayer
* refactor code
Change-Id: I3c5a9a4a60b74c2246b4a27692bbf3c235163f90
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
|
|
Change-Id: I2140a7af5961ddf8267fbb127202de3900ea79e3
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
* implementation of DetectionPostProcessQueueDescriptor validate
* add Uint8ToFloat32Workload
* add implementation of Detection PostProcess functionalities
* add ref workload implemenentation for float and uint8
* add layer support for Detection PostProcess in ref
* unit tests
Change-Id: I650461f49edbb3c533d68ef8700377af51bc3592
|
|
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
|
|
* Create the required ConstTensors and pass them to the appropriate
visit method. Back fill of dummies added during IVGCVSW-2547
* Moved the VisitDetectionPostProcessLayer function declaration in
ILayerVistor to its correct location after the
VisitDepthwiseConvolution2dLayer functions.
Change-Id: I0bd2f8c3603cbdb933b1216ead96dd8273eb5013
|
|
* Add DetectionPostProcessDescriptor.
* Add implementation for DetectionPostProcessLayer.
* Unit test to validate output.
Change-Id: If63e83eb2a2978c549071c7aeb272906e7c35fe9
|
|
* Layers which callback VisitXXXLayer with ConstTensor
have been implemented with dummies to speed up implementation
and unblock IVGCVSW-2531
Change-Id: I49b8035f12ec72d6bd6cee95075692f98c48e193
|
|
* 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
|
|
Change-Id: I803de435a538856de2daa7872e27d3f5beabba4f
|
|
* 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: I0ab3339e8803a3e4e700d8fec9883eccc524b31e
|
|
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
|
|
*Added Unit Tests
Change-Id: I6cceb8e6dcda35ce08415f8e5ca86019a64d26e3
|
|
* Add documentation to the Descriptors
* Add documentation to the layers
Change-Id: I5e0849753903565227fd47d329a600fd90b2feb9
|
|
!android-nn-driver:428
Change-Id: I42e59ad96d2c80f46b085182855d34b710a74dfe
|
|
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
|
|
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
|
|
Change-Id: Ifd28e049192e6f5fe5c0f5d358afb2b530eef882
|
|
* Modified optimizer to support debug mode via DebugLayer
Change-Id: Ic8f313778e55540c182cf99876c44a0823be04c6
|
|
* 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
|
|
Change-Id: I6b26c681989ef815752186f027a245ef8da7aea2
|
|
Change-Id: I5455b720565248ff94278e76887d63f8434a7b58
|
|
Change-Id: I03fa374fd9692d98257de709f8c3ad0a49c88b95
|
|
Change-Id: I8964f5e8978c2d2a07734a381e3f7c656c22456a
|
|
Change-Id: Ic772acf481caed6e8a6b99f68a63dfc2a34c24dc
|
|
Change-Id: Ib2bf543fc4f855da94eb1d34a91637f7868321cd
|
|
Change-Id: I40acb42360bfcda09485efb2a54144d8e35bdafb
|
|
Change-Id: Ifa88a879dd239f60ab27330d6b73859393828ef0
|
|
Change-Id: If8d8087d9d365e467d3ca9bf9c40d7219cb75cfd
|