AI Benchmark: Running Deep Neural Networks on Android Smartphones 

Author:

00039- AI Benchmark: Running Deep Neural Networks on Android Smartphones

0. Abstract

In this paper, we present a study of the current state of deep learning in the Android ecosystem and describe available frameworks, programming models and the limitations of running AI on smartphones.

1. Introduction

Android Neural Networks API (NNAPI) [47], designed to run deep learning models on mobile devices.

We present an AI Benchmark designed specifically to test the machine learning performance, available hardware AI accelerators, chipset drivers, and memory limitations of the current Android devices.

2. Hardware Acceleration

2.1 Qualcomm chipsets / SNPE SDK

2.2 HiSilicon chipsets / Huawei HiAI SDK

2.3 MediaTek Chipsets / NeuroPilot SDK

2.4 Samsung chipsets

2.5 Google Pixel / Pixel Visual Core

00039- AI Benchmark: Running Deep Neural Networks on Android Smartphones

2.6 Arm Cortex CPUs / Mali GPUs / NN SDK

2.7 Android NNAPI

00039- AI Benchmark: Running Deep Neural Networks on Android Smartphones

3. Deep Learning Mobile Frameworks

3.1 TensorFlow Mobile

00039- AI Benchmark: Running Deep Neural Networks on Android Smartphones

3.2 TensorFlow Lite

3.3 Caffe2

4. AI Benchmark

The AI Benchmark is an Android application designed to check the performance and the memory limitations associated with running AI and deep learning algorithms on mobile platforms.

4.1 Deep Learning Tests

Test 1: Image Recognition ----MobileNet-V1

Test 2: Image Recoginition ---- Inception V3

Test 3: Face Reconginition ---- Inception-Resnet-V1 network

 the first three tests cur-rently represent a core set of architectures for classification problems that are suitable for mobile deployment.

Test 4: Imae Deblurring ---- SRCNN network

Test 5: Image Super-Resolution --- VDSR network

Test 6: Image Super-Resolution --- SRGAN model

Test 7: Image Semantic Segmentation --- ICNet CNN

Test 8: Image Enhancement --- DPED paper

Test 9: Memory Limitations --- SRCNN

00039- AI Benchmark: Running Deep Neural Networks on Android Smartphones

4.2 Technical Description

Use the TensorFlow Lite library

5 Benchmark Results

5.1 Neural Networks

5.2 Smartphones and mobile chipsets

  1. Qualcomm
  2. Huawei
  3. MediaTek
  4. Samsung

6 Discussion

00039- AI Benchmark: Running Deep Neural Networks on Android Smartphones

7 Conclusions

相关文章: