Age | Commit message (Collapse) | Author |
|
* BackendHelper.cpp IsXXXLayerSupported doesn't get as far as Neon/Cl
Validate functions where arm_compute::Status is returned.
* Conv2d, Depthwise, DilatedDepthwise and FullyConnected
* Tidy up if() -> if ()
* Clean up logic in FullyConnected so that isLayerSupported gets called
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I5da1a882f4a2f55e90aa984b2b9548a847cb3a2d
|
|
* IVGCVSW-6940 ConstTensorsAsInput: DepthwiseConvolution2d - Complete Neon and Cl Bug Fix
* Bug fix to enable Cl and Neon Backend Compatibility ConstantTensorsAsInputs
* Updated Cl and Neon FullyConnected workloads to handle constant
weights and bias as inputs rather than reading from member variables.
* Prevent non const weights and biases passing CL and NEON validate
for Depthwise Convolution.
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: I0f505ff5998a183152f843d0f6cc74327ba920e7
|
|
* Added backend specific optimization & test for CpuAcc and GpuAcc: PermuteDepthwiseConv2dWeights
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: I600476b2e9c557a39818a574c1091c9d650b21b1
|
|
* Neon workloads to extend NeonBaseWorkload instead of BaseWorkload
* Cl workload to extend ClBaseWorkload instead of BaseWorkload
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I8f39a31a89a8865ac4acf18573ab290d548d2864
|
|
Move the following header files from backendsCommon to armnn/backends.
* MemCopyWorkload.hpp
* TensorHandle.hpp
* Workload.hpp
* WorkloadData.hpp
* WorkloadFactory.hpp
Replace them with forwarding headers and a pragma deprecation message.
Resolve the deprecation messages in Arm NN code.
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: I47f116b30f86e478c9057795bc518c391a8ae514
|
|
Signed-off-by: Keith Davis <keith.davis@arm.com>
Change-Id: I7be77712a9f790928219ce91222d46cc766ab9dd
|
|
* This change is necessary because tflite uses a [1,H,W,I*M] format
and uses the I*M dimension for per axis quantization. Our previous
layout [M,I,H,W] can't handle the correlating quantization scales.
* Updates Onnx-, TfLiteParser and TfliteDelegate
* Updates the CpuRef, CpuAcc and GpuAcc backends
* Adjusts unit tests
* Adds test to ensure models with old layout can still be read and
executed
* Adds conversion function to previous layout [1,H,W,I*M] --> [M,I,H,W]
which can be used by backend developers
!android-nn-driver:5553
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: Ifef23368b8c3702cf315a5838d214f7dc13c0152
|
|
* Generalises ConstCpuTensorHandle and inherited
classes by removing 'Cpu' from aliases.
* New renamed classes: ConstTensorHandle, TensorHandle,
ScopedTensorHandle, PassthroughTensorHandle,
ConstPassthroughTensorHandle.
Signed-off-by: James Conroy <james.conroy@arm.com>
Change-Id: I1824e0e134202735fb77051f20a7252f161dfe16
|
|
* Added Fused Activation Optimization to both CL and Neon backends.
* Added Fused Activation support to all the CL and Neon workloads
that support it.
* Changed ProfilingTest network to be a Convolution layer
followed by an Abs layer rather than an Activation layer.
* Added IBackendInternal::OptimizeSubgraphView function that can accept a
ModelOptions.
* Network will now call OptimizeSubgraphView passing in the ModelOptions.
Signed-off-by: Keith Davis <keith.davis@arm.com>
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Ib536ac3cbafc7d9b35c139ad9a65b7735262cd9d
|
|
* Change boost assert to armnn assert
* Change include file to armnn assert
* Fix ARMNN_ASSERT_MSG issue with multiple conditions
* Change BOOST_ASSERT to BOOST_TEST where appropriate
* Remove unused include statements
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I5d0fa3a37b7c1c921216de68f0073aa34702c9ff
|
|
* Moved the relevant armnnUtils headers to the new location:
include/armnnUtils
* Update the header usage throughout the source code
!android-nn-driver:2387
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
Change-Id: I2ba15cebcacafad2b5a1a7b9c3312ffc585e09d6
|
|
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I8f698c6ec9826ce1188bc43bd59fbf7b83455c1a
|
|
* Add is_initalised() check to CLScheduler in
ClContextControl.
* Now use CLDepthwiseConvolutionLayer instead of
CLDepthwiseConvolutionLayer3x3.
* Now use NEDepthwiseConvolutionLayer instead of
NEDepthwiseConvolutionLayerOptimized.
!android-nn-driver:2212
Signed-off-by: James Conroy <james.conroy@arm.com>
Change-Id: I509af65315a4322dc820a5cc1bbd36ed6999b4a7
|
|
* Fix issued caused by layers with 5x5 filters and depth multipliers > 1
Signed-off-by: Matthew Jackson <matthew.jackson@arm.com>
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I58435a1f0e3c7e69861dc130fad525a01e2a849d
|
|
Change-Id: I5cd90121e5fe1b49b394ee6f5a87e86520a30119
Signed-off-by: Pablo Tello <pablo.tello@arm.com>
|
|
workloads
* Refactoring: use existing utility function for creating arm_compute::PadStrideInfo
objects in CL and NEON convolution workloads instead of duplicating code
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: Id5e5a0f264e20af99dabce8dd8c6b782dedb94e6
|
|
* Includes fixes for ResizeNearestNeighbor on CL and NEON
!android-nn-driver:1523
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I959e43cab21dce10a9072320fada11fcb57d41f2
|
|
Change-Id: Ia68da09d8f0fb0a04af9cb61062d7edaa5f1b887
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
Adds unit tests for dilated depthwise conv
Change-Id: Iad0a1b33d07fb0ef8f9f6edf0fd0f83a5800a36d
Signed-off-by: Bruno Goncalves <bruno.slackware@gmail.com>
Signed-off-by: Matthew Bentham <matthew.bentham@arm.com>
|
|
Added support for dilation in DepthwiseConvolution2d in the
Neon and CL backends.
Change-Id: Ie1522b498c07f80d6efcf9dc79e926c8cfa06ca5
Signed-off-by: Pablo Tello <pablo.tello@arm.com>
|
|
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
|
|
* 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
|
|
Change-Id: Icf7ef88a2eaef80ec32cc718b0ca9d26e830ed07
|
|
* 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
|
|
Includes a temporary workaround for COMPMID-1813
Change-Id: I3e5217281be072d5b61788ab8a75e818bbc5d247
|
|
Change-Id: I663a0a0fccb43ee960ec070121a59df9db0bb04e
|
|
Change-Id: I411d02949524eb802672d83ee281300c34b007c8
|