davisking/dlib

Feature: Android NN API usage

开放

#1,332 创建于 2018年5月26日

 (1 条评论) (0 个反应) (0 位负责人)C++ (3,442 个派生)batch import
help wanted

仓库指标

星标
 (14,432 个星标)
PR 合并指标
 (平均合并 3小时 56分钟) (30 天内合并 2 个 PR)

描述

Android now has a neural network API that delegates to NPU/DSP/GPU or falls back to CPU, on devices running Android 8.1 or higher. https://developer.android.com/ndk/guides/neuralnetworks/

Ideally there would be a backend in dlib to support this framework as it is likely going to be the most optimised pathway going forwards.

NNAPI is a bit limited in what it can do at this stage. It only does int8, int32 and float32 for types and a few dozen operations.

It was expanded in NNAPI 1.1, adding some more operations [Div/Mul/Pad/Mean/Sub] (which requires Android 9.0).

Example implementation can be found in the Tensorflow Lite library: https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/nnapi/NeuralNetworksShim.h

贡献者指南