Implementation of Deep-Learning based Image Classification on Single Board Computer

被引：0

作者：

Shiddieqy, Hasbi Ash ^{[1
]}

Hariadi, Farkhad Ihsan ^{[1
]}

Adiono, Trio ^{[1
]}

机构：

[1] Inst Teknol Bandung, Microelect Ctr, Sch Elect Engn & Informat, Jl Ganesha 10, Bandung 40132, Indonesia

来源：

2017 INTERNATIONAL SYMPOSIUM ON ELECTRONICS AND SMART DEVICES (ISESD) | 2017年

关键词：

Deep-Learning; Convolutional Neural Network; Loss function; Accuracy; Single Board Computer;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, a deep-learning agorithm based on convolutional neural-network is implemented using python and tflearn for image classification. A large number of different images which contains two types of animals, namely cat and dog are used for classification. Two different structures of CNN are used, namely with two and five layers. It is shown that the CNN with higher layer performs classification process with much higher accuracy. The best CNN model with high accuracy and small loss function deployed in single board computer.

引用

页码：133 / 137

页数：5