Age | Commit message (Collapse) | Author |
|
Signed-off-by: Ferran Balaguer <ferran.balaguer@arm.com>
Change-Id: I65ae8669d8365bf372fbf0d1eceb48cbe06ef92a
|
|
* Updated test/Android.mk file to be consistent with Android.mk
* Updated version number in androidnn.go to match with q-fsk
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I847f073d92457d59735b8f9ab14c7404cf5f9515
|
|
* Included required functions to the Android Q build by using macro
ARMNN_ANDROID_NN_V1_2
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
Change-Id: I3ea99ba4bebd85f0e8e69c72a90e1a7def4f9b35
|
|
with dilation params
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I51a9c71d7a277ab530ac35faea2e8a069c134f45
|
|
* Updated Android.mk to build HAL 1.2 driver
* Added 1.2 HalPolicy and ArmnnDriver
* Added 1.2 ArmnnPreparedModel
* Updated converters and utilities to accept new HAL 1.2 operands and operand types.
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I62856deab24e106f72cccce09468db4971756fa6
|
|
!armnn:1209
Change-Id: Ic493e5cdfe479e459342d7c7c9d77c63f859fa30
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
|
|
* Refactor Convolution2d Unit test for fp16Enabled
* Disable GpuAcc for Unit tests in Android Q
Signed-off-by: Kevin May <kevin.may@arm.com>
Change-Id: I9613eb325841bdf7d25abf51259fe2f5d973c929
|
|
* Updated Android.mk to build Android Q
* Added androidnn.go to inject cpp flags for Q
* Create Runtime when ACL is not enabled
Change-Id: Ia3e7a8e484fc81ce63998a65e29753cbf941173c
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Signed-off-by: Kevin May <kevin.may@arm.com>
|
|
* Updates on test classes.
Change-Id: I52e11a1d97d02c23e0a33e4e128dc43a4a95b5bc
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
|
|
Adds new unit test cases, and changes the implementation of
FlattenFullyConnectedInput to more closely match the documentation
of Android NNAPI.
Change-Id: I7ca96b1168b9c7bc78db66f53b0cc776153fd780
Signed-off-by: Matthew Bentham <matthew.bentham@arm.com>
|
|
Change-Id: Ia4dd63927a54aa0cc24d5a378f30189c957f12e8
Signed-off-by: Matthew Bentham <matthew.bentham@arm.com>
|
|
* Add fix for optional NO_VALUE operands in ConversionUtils.hpp
* Remove fail message for optional NO_VALUE in ConversionUtils.hpp
* Add to existing tests and test helper to cover optional NO_VALUE
Signed-off-by: Kevin May <kevin.may@arm.com>
Change-Id: Icf36af1fc00d3fb33cdd77ff6d6618cc4700d3fd
|
|
* Refactored the LSTM unit tests to avoid unnecessary copies
* Added new AddTensorOperand convenience function
* Fixed some required arguments in some tests
* Added new files to Android.bp
!armnn:124
Change-Id: I77ed22f2692d8aa46884b9ee31e48403f7299545
|
|
Mean layer
* Added unit tests (in a new file test/1.1/Mean.cpp)
* Refactored ArmnnDriverImpl to remove redundant tags in the log
messages
* Modified AddInputOperand to accept a quantized input tensor
Change-Id: Ie037ce426777daab28b0501124e1cc8686ad6184
|
|
Change-Id: I12e462c9a0a3613f0158f73929c566f53d1b3c76
|
|
Change-Id: I5b1209a871d0a848bb1fdfba5228f181e6968004
|
|
* Changed #if defined to #ifdef
* Simplified the Android ML namespace resolution
* Fixed the relative path in some include directives
Change-Id: I46e46faff98559c8042c1a4b8b82007f462df57d
|
|
before and after passing the FP16 flag in the Android-nn-driver
Change-Id: If8d4ca12421c3bee2526eec98f11d393af822373
|
|
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: Ibb7ed1e4e2191b9a978e26b5bacf916db403a60e
|
|
ALLOW_MISSING_DEPENDENCIES to true on Android versions that don't
provide all the HAL versions supported by the NN Driver
Change-Id: I7c828649499ca1d7cb26feb93f559e9f1eae33c7
|
|
|
|
|
|
|
|
|
|
Change-Id: I41a89c149534a7c354a58e2c66a32cba572fc0c1
|