Bug#952640: ITP: armnn -- Arm NN is an inference engine for CPUs, GPUs and NPUs

[Wookey <wookey@wookware.org>]

Package: wnpp
Severity: wishlist
Owner: Wookey <wookey@wookware.org>

* Package name    : armnn
  Version         : 19.11
  Upstream Author : ARM Ltd
* URL             : https://github.com/ARM-software/armnn
* License         : MIT
  Programming Lang: C++
  Description     : Arm NN is an inference engine for CPUs, GPUs and NPUs

 Arm NN is a set of tools that enables machine learning workloads on
 Arm hardware. It provides a bridge between existing neural network
 frameworks and whatever hardware is available: Cortex-A CPUs, Mali
 GPUs and Ethos NPUs. It utilizes the Arm Compute Library to target
 these programmable cores, as efficiently as possible. Arm NN does
 not provide support for Cortex-M CPUs.
 .
 The package is only available for arm64 and armhf architectures.

 This release supports Caffe, TensorFlow, TensorFlow Lite, and ONNX.
 Arm NN takes networks from these frameworks, translates them
 to the internal Arm NN format and then, through the Arm Compute Library,
 deploys them efficiently on Cortex-A CPUs, and, if present, Mali GPUs
 such as the Mali-G71 and Mali-G72. 

This package is part of the machine learning stack (on arm).
arm-compute-library, armnn, tvm, onnx etc.

It is developed under the Linaro Machine Intelligence Initiative 
(see mlplatform.org).