Age | Commit message (Collapse) | Author |
|
* 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: Kevin May <kevin.may@arm.com>
Change-Id: I7626d5bd82e832d5be6913719a34d76fbd1dbed8
|
|
Signed-off-by: Keith Davis <keith.davis@arm.com>
Change-Id: I92dd410da7ad633a46d025fdc2b26093041c439b
|
|
* 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
|
|
* Injected CLCompileContext object to each CL workload.
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I4837dbd3d5b56cf743b3b89c944e3cdf8b11a42a
|
|
* 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
|
|
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
|
|
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
|
|
Added support for dilation in DepthwiseConvolution2d in the
Neon and CL backends.
Change-Id: Ie1522b498c07f80d6efcf9dc79e926c8cfa06ca5
Signed-off-by: Pablo Tello <pablo.tello@arm.com>
|
|
!android-nn-driver:968
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I03ccb4842b060a9893567542bfcadc180bbc7311
|
|
* 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
|
|
DataLayout (3*3 Optimization)
Change-Id: Icfc137201c52e2c856076b7795572cc4ba75cc95
|
|
Change-Id: I663a0a0fccb43ee960ec070121a59df9db0bb04e
|
|
* Added wrapper function around arm_compute::IFunction::run() that catches
cl::Error and wraps it into an armnn::RuntimeException
* Added MakeWorkload template inside ClWorkloadFactory that catches
cl::Error and wraps it into an armnn::RuntimeException
* Replaced cl::Error with armnn::RuntimeException in catch statements inside
LoadedNetwork
Change-Id: I2340f41ae02b8db1d7ef5157824a50e7410854e3
|
|
Change-Id: I3e6e5b9a62f30d03c05bd7178adea8f4c8275da8
|
|
Change-Id: I8bc11c93759605e21cc52f44d032c32a0be63658
|