Age | Commit message (Collapse) | Author |
|
* 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
|
|
* Add new class ManagedConstTensorHandle to Unmap when out of scope
* Integrate into existing layers that have constants
* Add unit tests
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: I0a05e14e438804b37e9862e76b5ca329483f6b45
|
|
* Change layer storage of ConstTensors to std::shared_ptr<ConstCpuTensorHandle>
* Change clone to share ConstTensor rather than copy
* Remove uses of non-const GetTensor() call
* Reduce scope of non-optimized network in ExeNet, so memory can be released after use
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: Ibb2c7309d12411d21405bd6024c76bcdf5404545
|
|
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: Id7bc8255a8e3f9e5aac65d510bec8a559bf37246
|
|
* Convolution
* Depthwise Convolution
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I61b356fbffb176e9a05e08d9b6867d082b6712c8
|
|
Signed-off-by: Keith Davis <keith.davis@arm.com>
Change-Id: I0a07dea96a86849701ba387dbea148909a6d729b
|
|
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I0a2babe5b5b09eb81c9900dc3a05071034a0440b
|
|
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I2c2d99f97cf89814140b057a9f93f41b364197f5
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I70ef1a9f3cefa1d4cf9220f0e13131d11e7c6418
|
|
* 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
|
|
Change-Id: I649cd2304fb0040164763d31a12fc77c6c3bed87
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
* 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
|
|
* Generic layer parameters now show up in dot file
* Convolution layer parameters have also been added to dot file
* ExecucteNetwork has an additional -v flag which generated dot file if there
Change-Id: I210bb19b45384eb3639b7e488c7a89049fa6f18d
Signed-off-by: Andre Ghattas <andre.ghattas@arm.com>
Signed-off-by: Szilard Papp <szilard.papp@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>
|
|
DepthwiseConvolution2D and FullyConnected
Change-Id: I3048504ff699fdb266488e7c07b7262e5843d4b0
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
|
|
Change-Id: I20a67135e4af7aa1f28f5000d73122f4e5e3acd5
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
|
|
* 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
|
|
* Layers which callback VisitXXXLayer with ConstTensor
have been implemented with dummies to speed up implementation
and unblock IVGCVSW-2531
Change-Id: I49b8035f12ec72d6bd6cee95075692f98c48e193
|
|
* 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
|
|
* 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: If8d8087d9d365e467d3ca9bf9c40d7219cb75cfd
|
|
Change-Id: I663a0a0fccb43ee960ec070121a59df9db0bb04e
|
|
shape in ValidateTensorShapesFromInputs
* Convolution2dLayer
* DepthwiseConvolution2dLayer
* Pooling2dLayer
* ResizeBilinearLayer
* Unittests for ValidateTensorShapesFromInputs
Change-Id: I057caf8a90d822175a7dd7271f960b65c6154bb4
|
|
Change-Id: I3e6e5b9a62f30d03c05bd7178adea8f4c8275da8
|
|
Change-Id: Ia14c9d8c0a38b669a7589e63d74424e398790e54
|
|
All changes are the same:
//
// Copyright © 2017 ARM Ltd. All rights reserved.
-// See LICENSE file in the project root for full license information.
+// SPDX-License-Identifier: MIT
//
Change-Id: I37eae011411133663ca9d2b059714d92f8bf8e24
|
|
|
|
|