Bug: 161933712

Clone this repo:
  1. 094cd64 Merge sc-mainline-prod by Xin Li · 1 year, 8 months ago android13-dev android13-frc-adbd-release android13-frc-art-release android13-frc-cellbroadcast-release android13-frc-conscrypt-release android13-frc-documentsui-release android13-frc-extservices-release android13-frc-ipsec-release android13-frc-media-release android13-frc-media-swcodec-release android13-frc-networking-release android13-frc-neuralnetworks-release android13-frc-os-statsd-release android13-frc-permission-release android13-frc-resolv-release android13-frc-scheduling-release android13-mainline-adservices-release android13-mainline-appsearch-release android13-mainline-go-adbd-release android13-mainline-go-adservices-release android13-mainline-go-appsearch-release android13-mainline-go-art-release android13-mainline-go-cellbroadcast-release android13-mainline-go-conscrypt-release android13-mainline-go-documentsui-release android13-mainline-go-extservices-release android13-mainline-go-ipsec-release android13-mainline-go-media-release android13-mainline-go-media-swcodec-release android13-mainline-go-mediaprovider-release android13-mainline-go-networking-release android13-mainline-go-neuralnetworks-release android13-mainline-go-odp-release android13-mainline-go-os-statsd-release android13-mainline-go-permission-release android13-mainline-go-resolv-release android13-mainline-go-scheduling-release android13-mainline-go-sdkext-release android13-mainline-go-tethering-release android13-mainline-go-tzdata4-release android13-mainline-go-uwb-release android13-mainline-go-wifi-release android13-mainline-tzdata4-release android13-mainline-uwb-release android13-platform-release android13-qpr1-release android13-qpr1-s1-release android13-qpr1-s2-release android13-qpr1-s3-release android13-qpr1-s4-release android13-qpr1-s5-release main-16k main-16k-with-phones master aml_ads_331131000 aml_ase_331011020 aml_ase_331112000 aml_go_adb_330913000 aml_go_ads_330913000 aml_go_art_330913000 aml_go_ase_330913000 aml_go_cbr_330912000 aml_go_con_330913000 aml_go_doc_330912000 aml_go_ext_330912000 aml_go_ips_330911000 aml_go_med_330913000 aml_go_mpr_330912000 aml_go_net_330913000 aml_go_neu_330912000 aml_go_odp_330912000 aml_go_per_330912000 aml_go_res_330912000 aml_go_sch_330911000 aml_go_sdk_330810000 aml_go_sta_330911000 aml_go_swc_330913000 aml_go_tet_330914010 aml_go_tz4_330912000 aml_go_uwb_330912000 aml_go_wif_330911000 aml_tz4_331012000 aml_tz4_331012040 aml_tz4_331012050 aml_tz4_331314010 aml_uwb_330810010 aml_uwb_331015040 aml_uwb_331115000 aml_uwb_331310030 android-13.0.0_r16 android-13.0.0_r17 android-13.0.0_r18 android-13.0.0_r19 android-13.0.0_r20 android-13.0.0_r21 android-13.0.0_r22 android-13.0.0_r23 android-13.0.0_r24 android-platform-13.0.0_r1 t_frc_adb_330444000 t_frc_art_330443060 t_frc_ase_330444010 t_frc_cbr_330443000 t_frc_con_330443020 t_frc_doc_330443000 t_frc_doc_330443060 t_frc_doc_330543000 t_frc_ext_330443000 t_frc_ips_330443010 t_frc_med_330443030 t_frc_net_330443000 t_frc_neu_330443000 t_frc_neu_330443030 t_frc_odp_330442000 t_frc_per_330444010 t_frc_res_330443000 t_frc_sch_330443010 t_frc_sch_330443040 t_frc_sta_330443010 t_frc_swc_330443010 t_frc_swc_330443040 t_frc_tz4_330443010
  2. 6aee581 [LSC] Add LOCAL_LICENSE_KINDS to external/armnn am: c768eebe89 by Bob Badour · 1 year, 10 months ago android12-mainline-adbd-release android12-mainline-art-release android12-mainline-captiveportallogin-release android12-mainline-cellbroadcast-release android12-mainline-conscrypt-release android12-mainline-documentsui-release android12-mainline-extservices-release android12-mainline-ipsec-release android12-mainline-media-release android12-mainline-media-swcodec-release android12-mainline-mediaprovider-release android12-mainline-networkstack-release android12-mainline-neuralnetworks-release android12-mainline-permission-release android12-mainline-resolv-release android12-mainline-sdkext-release android12-mainline-statsd-release android12-mainline-tethering-release android12-mainline-wifi-release aml_doc_310851020 aml_mpr_311911090 aml_sdk_311710000 aml_tet_311811050 aml_tz3_311312010 aml_wif_311811030 android-mainline-12.0.0_r1 android-mainline-12.0.0_r10 android-mainline-12.0.0_r100 android-mainline-12.0.0_r101 android-mainline-12.0.0_r102 android-mainline-12.0.0_r103 android-mainline-12.0.0_r104 android-mainline-12.0.0_r105 android-mainline-12.0.0_r106 android-mainline-12.0.0_r107 android-mainline-12.0.0_r108 android-mainline-12.0.0_r109 android-mainline-12.0.0_r11 android-mainline-12.0.0_r110 android-mainline-12.0.0_r113 android-mainline-12.0.0_r114 android-mainline-12.0.0_r115 android-mainline-12.0.0_r116 android-mainline-12.0.0_r117 android-mainline-12.0.0_r118 android-mainline-12.0.0_r119 android-mainline-12.0.0_r12 android-mainline-12.0.0_r120 android-mainline-12.0.0_r121 android-mainline-12.0.0_r122 android-mainline-12.0.0_r123 android-mainline-12.0.0_r124 android-mainline-12.0.0_r125 android-mainline-12.0.0_r126 android-mainline-12.0.0_r13 android-mainline-12.0.0_r14 android-mainline-12.0.0_r15 android-mainline-12.0.0_r16 android-mainline-12.0.0_r17 android-mainline-12.0.0_r18 android-mainline-12.0.0_r19 android-mainline-12.0.0_r2 android-mainline-12.0.0_r20 android-mainline-12.0.0_r21 android-mainline-12.0.0_r22 android-mainline-12.0.0_r23 android-mainline-12.0.0_r24 android-mainline-12.0.0_r25 android-mainline-12.0.0_r26 android-mainline-12.0.0_r27 android-mainline-12.0.0_r28 android-mainline-12.0.0_r29 android-mainline-12.0.0_r3 android-mainline-12.0.0_r30 android-mainline-12.0.0_r31 android-mainline-12.0.0_r32 android-mainline-12.0.0_r33 android-mainline-12.0.0_r34 android-mainline-12.0.0_r35 android-mainline-12.0.0_r37 android-mainline-12.0.0_r38 android-mainline-12.0.0_r39 android-mainline-12.0.0_r40 android-mainline-12.0.0_r41 android-mainline-12.0.0_r42 android-mainline-12.0.0_r43 android-mainline-12.0.0_r44 android-mainline-12.0.0_r45 android-mainline-12.0.0_r46 android-mainline-12.0.0_r47 android-mainline-12.0.0_r48 android-mainline-12.0.0_r49 android-mainline-12.0.0_r5 android-mainline-12.0.0_r50 android-mainline-12.0.0_r51 android-mainline-12.0.0_r52 android-mainline-12.0.0_r53 android-mainline-12.0.0_r56 android-mainline-12.0.0_r57 android-mainline-12.0.0_r58 android-mainline-12.0.0_r59 android-mainline-12.0.0_r6 android-mainline-12.0.0_r60 android-mainline-12.0.0_r61 android-mainline-12.0.0_r62 android-mainline-12.0.0_r63 android-mainline-12.0.0_r64 android-mainline-12.0.0_r65 android-mainline-12.0.0_r66 android-mainline-12.0.0_r67 android-mainline-12.0.0_r68 android-mainline-12.0.0_r69 android-mainline-12.0.0_r7 android-mainline-12.0.0_r70 android-mainline-12.0.0_r71 android-mainline-12.0.0_r72 android-mainline-12.0.0_r73 android-mainline-12.0.0_r74 android-mainline-12.0.0_r75 android-mainline-12.0.0_r76 android-mainline-12.0.0_r77 android-mainline-12.0.0_r78 android-mainline-12.0.0_r79 android-mainline-12.0.0_r8 android-mainline-12.0.0_r80 android-mainline-12.0.0_r81 android-mainline-12.0.0_r82 android-mainline-12.0.0_r83 android-mainline-12.0.0_r84 android-mainline-12.0.0_r85 android-mainline-12.0.0_r86 android-mainline-12.0.0_r87 android-mainline-12.0.0_r88 android-mainline-12.0.0_r89 android-mainline-12.0.0_r9 android-mainline-12.0.0_r90 android-mainline-12.0.0_r91 android-mainline-12.0.0_r92 android-mainline-12.0.0_r93 android-mainline-12.0.0_r94 android-mainline-12.0.0_r95 android-mainline-12.0.0_r96 android-mainline-12.0.0_r97 android-mainline-12.0.0_r98 android-mainline-12.0.0_r99
  3. 80aec38 [LSC] Add LOCAL_LICENSE_KINDS to external/armnn am: c768eebe89 by Bob Badour · 1 year, 10 months ago
  4. c768eeb [LSC] Add LOCAL_LICENSE_KINDS to external/armnn by Bob Badour · 1 year, 10 months ago android12-qpr1-d-release android12-qpr1-d-s1-release android12-qpr1-d-s2-release android12-qpr1-d-s3-release android12-qpr3-release android12-qpr3-s1-release android12-qpr3-s2-release android12-qpr3-s3-release android12-qpr3-s4-release android12-qpr3-s5-release android12-qpr3-s6-release android12-qpr3-s7-release android12L-d2-release android12L-d2-s1-release android12L-d2-s2-release android12L-d2-s3-release android12L-d2-s4-release android12L-d2-s5-release android12L-d2-s6-release android12L-d2-s7-release android12L-d2-s8-release android12L-dev main-cg-testing-release android-12.0.0_r18 android-12.0.0_r19 android-12.0.0_r20 android-12.0.0_r21 android-12.0.0_r27 android-12.0.0_r29 android-12.0.0_r32 android-12.1.0_r10 android-12.1.0_r11 android-12.1.0_r12 android-12.1.0_r13 android-12.1.0_r14 android-12.1.0_r15 android-12.1.0_r16 android-12.1.0_r17 android-12.1.0_r18 android-12.1.0_r19 android-12.1.0_r20 android-12.1.0_r21 android-12.1.0_r22 android-12.1.0_r23 android-12.1.0_r24 android-12.1.0_r25 android-12.1.0_r26 android-12.1.0_r7 android-12.1.0_r8 android-12.1.0_r9 platform-tools-32.0.0 platform-tools-33.0.0 platform-tools-33.0.1 platform-tools-33.0.2
  5. bea42f3 armnn: sync to 20.11 release am: a6543fa3a9 by Kevin DuBois · 2 years ago

Arm NN

Arm NN is a key component of the machine learning platform, which is part of the Linaro Machine Intelligence Initiative. For more information on the machine learning platform and Arm NN, see: https://mlplatform.org/, also there is further Arm NN information available from https://developer.arm.com/products/processors/machine-learning/arm-nn

There is a getting started guide here using TensorFlow: https://developer.arm.com/solutions/machine-learning-on-arm/developer-material/how-to-guides/configuring-the-arm-nn-sdk-build-environment-for-tensorflow

There is a getting started guide here using TensorFlow Lite: https://developer.arm.com/solutions/machine-learning-on-arm/developer-material/how-to-guides/configuring-the-arm-nn-sdk-build-environment-for-tensorflow-lite

There is a getting started guide here using Caffe: https://developer.arm.com/solutions/machine-learning-on-arm/developer-material/how-to-guides/configure-the-arm-nn-sdk-build-environment-for-caffe

There is a getting started guide here using ONNX: https://developer.arm.com/solutions/machine-learning-on-arm/developer-material/how-to-guides/configuring-the-arm-nn-sdk-build-environment-for-onnx

There is a guide for backend development: Backend development guide

There is a guide for installation of ArmNN, Tensorflow Lite Parser and PyArmnn via our Apt Repository: Installation via Apt Repository

There is a getting started guide for our ArmNN TfLite Delegate: Build the TfLite Delegate natively

API Documentation is available at https://github.com/ARM-software/armnn/wiki/Documentation.

Dox files to generate Arm NN doxygen files can be found at armnn/docs/. Following generation the xhtml files can be found at armnn/documentation/

Build Instructions

Arm tests the build system of Arm NN with the following build environments:

Arm NN is written using portable C++14 and the build system uses CMake, therefore it is possible to build for a wide variety of target platforms, from a wide variety of host environments.

The armnn/tests directory contains tests used during Arm NN development. Many of them depend on third-party IP, model protobufs and image files not distributed with Arm NN. The dependencies of some of the tests are available freely on the Internet, for those who wish to experiment.

The ‘armnn/samples’ directory contains SimpleSample.cpp, a very basic example of the ArmNN SDK API in use, and DynamicSample.cpp, a very basic example of using the ArmNN SDK API with the standalone sample dynamic backend.

The ‘ExecuteNetwork’ program, in armnn/tests/ExecuteNetwork, has no additional dependencies beyond those required by Arm NN and the model parsers. It takes any model and any input tensor, and simply prints out the output tensor. Run it with no arguments to see command-line help.

The ‘ArmnnConverter’ program, in armnn/src/armnnConverter, has no additional dependencies beyond those required by Arm NN and the model parsers. It takes a model in TensorFlow format and produces a serialized model in Arm NN format. Run it with no arguments to see command-line help. Note that this program can only convert models for which all operations are supported by the serialization tool src/armnnSerializer.

The ‘ArmnnQuantizer’ program, in armnn/src/armnnQuantizer, has no additional dependencies beyond those required by Arm NN and the model parsers. It takes a 32-bit float network and converts it into a quantized asymmetric 8-bit or quantized symmetric 16-bit network. Static quantization is supported by default but dynamic quantization can be enabled if CSV file of raw input tensors is specified. Run it with no arguments to see command-line help.

Note that Arm NN needs to be built against a particular version of ARM's Compute Library. The get_compute_library.sh in the scripts subdirectory will clone the compute library from the review.mlplatform.org github repository into a directory alongside armnn named ‘clframework’ and checks out the correct revision.

For FAQs and troubleshooting advice, see FAQ.md

License

Arm NN is provided under the MIT license. See LICENSE for more information. Contributions to this project are accepted under the same license.

Individual files contain the following tag instead of the full license text.

SPDX-License-Identifier: MIT

This enables machine processing of license information based on the SPDX License Identifiers that are available here: http://spdx.org/licenses/

Third party tools used by Arm NN:

ToolLicense (SPDX ID)DescriptionVersionProvenience
cxxoptsMITA lightweight C++ option parser librarySHA 12e496da3d486b87fa9df43edea65232ed852510https://github.com/jarro2783/cxxopts
fmtMIT{fmt} is an open-source formatting library providing a fast and safe alternative to C stdio and C++ iostreams.7.0.1https://github.com/fmtlib/fmt
ghcMITA header-only single-file std::filesystem compatible helper library1.3.2https://github.com/gulrak/filesystem
halfMITIEEE 754 conformant 16-bit half-precision floating point library1.12.0http://half.sourceforge.net
mapbox/variantBSDA header-only alternative to ‘boost::variant’1.1.3https://github.com/mapbox/variant
stbMITImage loader, resize and writer2.16https://github.com/nothings/stb

Contributions

The Arm NN project welcomes contributions. For more details on contributing to Arm NN see the Contributing page on the MLPlatform.org website, or see the Contributor Guide.