基于Java实现CNN，并附MNIST和语音（MFCC特征）性别识别示例。
构建CNN
LayerBuilder builder = new LayerBuilder();
builder.addLayer(Layer.buildInputLayer(new Size(28, 28)));
builder.addLayer(Layer.buildConvLayer(6, new Size(5, 5)));
builder.addLayer(Layer.buildSampLayer(new Size(2, 2)));
builder.addLayer(Layer.buildConvLayer(12, new Size(5, 5)));
builder.addLayer(Layer.buildSampLayer(new Size(2, 2)));
builder.addLayer(Layer.buildOutputLayer(10));
CNN cnn = new CNN(builder, 50);
运行MNIST数据集
String fileName = "data/train.format";
Dataset dataset = Dataset.load(fileName, ",", 784);
cnn.train(dataset, 100);
Dataset testset = Dataset.load("data/test.format", ",", -1);
cnn.predict(testset, "data/test.predict");
计算精度可以达到97.8%。
文件下载
资源详情
[{"title":"（ 24 个子文件 1.87MB ） 基于Java实现CNN，并附MNIST和语音（MFCC特征）性别识别示例。","children":[{"title":"cnn-master","children":[{"title":"src","children":[{"title":"test","children":[{"title":"resources","children":[{"title":"logback-test.xml <span style='color:#111;'> 411B </span>","children":null,"spread":false}],"spread":true},{"title":"java","children":[{"title":"info","children":[{"title":"hb","children":[{"title":"cnn","children":[{"title":"utils","children":[{"title":"TimedTest.java <span style='color:#111;'> 474B </span>","children":null,"spread":false},{"title":"TestArray.java <span style='color:#111;'> 1.44KB </span>","children":null,"spread":false},{"title":"MathUtilsTest.java <span style='color:#111;'> 3.82KB </span>","children":null,"spread":false}],"spread":true},{"title":"data","children":[{"title":"DataSetTest.java <span style='color:#111;'> 460B </span>","children":null,"spread":false}],"spread":true}],"spread":true}],"spread":true}],"spread":true}],"spread":true}],"spread":true},{"title":"main","children":[{"title":"resources","children":[{"title":"logback.xml <span style='color:#111;'> 1.11KB </span>","children":null,"spread":false}],"spread":true},{"title":"java","children":[{"title":"info","children":[{"title":"hb","children":[{"title":"ccn","children":[{"title":"main","children":[{"title":"CNNSpeech.java <span style='color:#111;'> 1.64KB </span>","children":null,"spread":false},{"title":"CNNMnist.java <span style='color:#111;'> 1.84KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"cnn","children":[{"title":"utils","children":[{"title":"ConcurentRunner.java <span style='color:#111;'> 1.90KB </span>","children":null,"spread":false},{"title":"MathUtils.java <span style='color:#111;'> 8.97KB </span>","children":null,"spread":false}],"spread":true},{"title":"core","children":[{"title":"CNN.java <span style='color:#111;'> 14.58KB </span>","children":null,"spread":false},{"title":"Layer.java <span style='color:#111;'> 5.75KB </span>","children":null,"spread":false}],"spread":true},{"title":"data","children":[{"title":"DataSet.java <span style='color:#111;'> 3.63KB </span>","children":null,"spread":false}],"spread":true}],"spread":true}],"spread":true}],"spread":true}],"spread":true}],"spread":true}],"spread":true},{"title":"speech","children":[{"title":"test.predict <span style='color:#111;'> 86B </span>","children":null,"spread":false},{"title":"test.label <span style='color:#111;'> 86B </span>","children":null,"spread":false},{"title":"model","children":[{"title":"model.cnn <span style='color:#111;'> 16.33KB </span>","children":null,"spread":false}],"spread":true},{"title":"test.format <span style='color:#111;'> 30.38KB </span>","children":null,"spread":false},{"title":"train.format <span style='color:#111;'> 141.08KB </span>","children":null,"spread":false}],"spread":true},{"title":"README.md <span style='color:#111;'> 754B </span>","children":null,"spread":false},{"title":"mnist","children":[{"title":"test.format <span style='color:#111;'> 41.87MB </span>","children":null,"spread":false},{"title":"readme.md <span style='color:#111;'> 208B </span>","children":null,"spread":false},{"title":"train.format <span style='color:#111;'> 17.97MB </span>","children":null,"spread":false}],"spread":true},{"title":"pom.xml <span style='color:#111;'> 2.95KB </span>","children":null,"spread":false},{"title":".gitignore <span style='color:#111;'> 45B </span>","children":null,"spread":false}],"spread":true}],"spread":true}]
评论信息
其他资源
- STM8S003F3_HXD019D红外遥控程序.zip
- 中信银行计算机考试题
- 精通matlab最优化计算的随书源码（包括混沌搜索等）
- 模拟电路课程设计—波形发生器
- JSCH处理输入pssword的源代码
- 数字图像修复技术的背景，目的和意义
- java实现聊天室功能（全部代码，有界面）
- 计算机网络课程设计（小型校园局域网组建）
- 下采样Matlab实例
- 磁耦合谐振式充电系统RLC谐振仿真
- eCognition8软件下载及破解教程
- Java多线程编程实战指南(核心篇)
- opencv 3.4.X 编译 ffmpeg和ippicv相关资源
- AB PLC 与 PC 通过 socket 通讯文档
- FastStone Capture7.7简体中文破解版
- 蝶形多模干涉耦合器的数值分析
- PLSQL_Developer.zip
- terraform-provider-alicloud：Terraform AliCloud提供程序-源码
- BinToos_2.exe
- Linux系统配置及服务管理_第05章_重定向管道.doc
- sentinl-v6.3.1.zip
- JDK API 1.8.CHM
- freeICTCLAS中科院中文分词(拼音中文输入法设计和源代码).zip
- 一种基于属性重要性的变精度粗糙集属性约简算法
- 冷却塔选型计算公式，冷却塔选型计算公式，方便制冷工作者快速计算出冷却塔所需的各项数据及大小
- AS SSD Benchmark (固态硬盘测试软件）
免责申明
【只为小站】的资源来自网友分享，仅供学习研究，请务必在下载后24小时内给予删除，不得用于其他任何用途，否则后果自负。基于互联网的特殊性，【只为小站】 无法对用户传输的作品、信息、内容的权属或合法性、合规性、真实性、科学性、完整权、有效性等进行实质审查；无论 【只为小站】 经营者是否已进行审查，用户均应自行承担因其传输的作品、信息、内容而可能或已经产生的侵权或权属纠纷等法律责任。
本站所有资源不代表本站的观点或立场，基于网友分享，根据中国法律《信息网络传播权保护条例》第二十二条之规定，若资源存在侵权或相关问题请联系本站客服人员，zhiweidada#qq.com，请把#换成@，本站将给予最大的支持与配合，做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明
本站所有资源不代表本站的观点或立场，基于网友分享，根据中国法律《信息网络传播权保护条例》第二十二条之规定，若资源存在侵权或相关问题请联系本站客服人员，zhiweidada#qq.com，请把#换成@，本站将给予最大的支持与配合，做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明