Arm NN is a key component of the machine learning platform, which is part of the Linaro Machine Intelligence Initiative.
The Arm NN SDK is a set of open-source software and tools that enables machine learning workloads on power-efficient devices. It provides a bridge between existing neural network frameworks and power-efficient Cortex-A CPUs, Arm Mali GPUs and Arm Ethos NPUs.
Arm NN SDK utilizes the Compute Library to target programmable cores, such as Cortex-A CPUs and Mali GPUs, as efficiently as possible. To target Ethos NPUs the NPU-Driver is utilized. We also welcome new contributors to provide their own driver and backend. Note, Arm NN does not provide support for Cortex-M CPUs.
The latest release supports models created with Caffe, TensorFlow, TensorFlow Lite (TfLite) and ONNX. Arm NN analysis a given model and replaces the operations within it with implementations particularly designed for the hardware you want to execute it on. This results in a great boost of execution speed. How much faster your neural network can be executed depends on the operations it contains and the available hardware. Below you can see the speedup we've been experiencing in our experiments with a few common networks.
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.
Depending on what kind of framework (Tensorflow, Caffe, ONNX) you've been using to create your model there are multiple software tools available within Arm NN that can serve your needs.
Generally, there is a parser available for each supported framework. Each parser allows you to run models from one framework e.g. the TfLite-Parser lets you run TfLite models. You can integrate these parsers into your own application to load, optimize and execute your model. We also provide python bindings for our parsers and the Arm NN core. We call the result PyArmNN. Therefore your application can be conveniently written in either C++ using the "original" Arm NN library or in Python using PyArmNN. You can find tutorials on how to setup and use our parsers in our doxygen documentation. The latest version can be found in the wiki section of this repository.
Admittedly, building Arm NN and its parsers from source is not always easy to accomplish. We are trying to increase our usability by providing Arm NN as a Debian package. Our debian package is the most easy way to install the Arm NN Core, the TfLite Parser and PyArmNN (More support is about to come): Installation via Apt Repository
The newest member in Arm NNs software toolkit is the TfLite Delegate. The delegate can be integrated in TfLite. TfLite will then delegate operations, that can be accelerated with Arm NN, to Arm NN. Every other operation will still be executed with the usual TfLite runtime. This is our recommended way to accelerate TfLite models. As with our parsers there are tutorials in our doxygen documentation that can be found in the wiki section.
If you would like to use Arm NN on Android you can follow this guide which explains how to build Arm NN using the AndroidNDK. But you might also want to take a look at another repository which implements a hardware abstraction layer (HAL) for Android. The repository is called Android-NN-Driver and when integrated into Android it will automatically run neural networks with Arm NN.
The section above introduces the most important tools that Arm NN provides. You can find a complete list in our doxygen documentation. The latest version can be found in the wiki section of our github repository.
For FAQs and troubleshooting advice, see FAQ.md or take a look at previous github issues.
-
The following tools are deprecated in Arm NN 21.02 and will be removed in 21.05:
- TensorflowParser
- CaffeParser
- Quantizer
-
We are currently in the process of removing boost as a dependency to Arm NN. This process is finished for everything apart from our unit tests. This means you don't need boost to build and use Arm NN but you need it to execute our unit tests. Boost will soon be removed from Arm NN entirely.
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.
Particularly if you'd like to implement your own backend next to our CPU, GPU and NPU backends there are guides for backend development: Backend development guide, Dynamic backend development guide
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, but they won't run out of the box.
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:
| Tool | License (SPDX ID) | Description | Version | Provenience |
|---|---|---|---|---|
| cxxopts | MIT | A lightweight C++ option parser library | SHA 12e496da3d486b87fa9df43edea65232ed852510 | https://github.com/jarro2783/cxxopts |
| fmt | MIT | {fmt} is an open-source formatting library providing a fast and safe alternative to C stdio and C++ iostreams. | 7.0.1 | https://github.com/fmtlib/fmt |
| ghc | MIT | A header-only single-file std::filesystem compatible helper library | 1.3.2 | https://github.com/gulrak/filesystem |
| half | MIT | IEEE 754 conformant 16-bit half-precision floating point library | 1.12.0 | http://half.sourceforge.net |
| mapbox/variant | BSD | A header-only alternative to 'boost::variant' | 1.1.3 | https://github.com/mapbox/variant |
| stb | MIT | Image loader, resize and writer | 2.16 | https://github.com/nothings/stb |