mnist项目.zip

上传者: free_girl_fang | 上传时间: 2021-06-27 19:07:41 | 文件大小: 54.31MB | 文件类型: ZIP
实验的训练集选择为mnist数据集的20000张像素为28*28的手写体,10000张像素为28*28的手写体中选择2000张作为验证集,8000张作为实验的测试集。 实验在验证集上选择超参数5个学习率要求,选择最高的模型 此时我们固定其他参数做五组不同的实验查看验证集的准确率结果,由于在步骤2中使用的批量是150 所以要在其周围寻找比较合适的批量个数。实验中固定其他参数,使用不同的学习率进行实验,由于在步骤2中我们已经选择了效果比较的的学习率为0.0001 ,步骤3中我们已经选择了效果比较的的小批量为100则以此为基础,固定其他参数,进行实验。实验中固定其他参数,使用不同的卷积神经网络时卷积核的大小进行实验

文件下载

资源详情

[{"title":"( 24 个子文件 54.31MB ) mnist项目.zip","children":[{"title":"mnist项目","children":[{"title":"mnist3","children":[{"title":"myCNN3.m <span style='color:#111;'> 2.72KB </span>","children":null,"spread":false},{"title":"myCNN1.asv <span style='color:#111;'> 2.77KB </span>","children":null,"spread":false},{"title":"mnist_uint8.mat <span style='color:#111;'> 14.05MB </span>","children":null,"spread":false}],"spread":true},{"title":"loadMNISTImages.m <span style='color:#111;'> 811B </span>","children":null,"spread":false},{"title":"mnist1","children":[{"title":"loadMNISTImages.m <span style='color:#111;'> 811B </span>","children":null,"spread":false},{"title":"cnnPool.m <span style='color:#111;'> 1.50KB </span>","children":null,"spread":false},{"title":"myCNN1.m <span style='color:#111;'> 10.79KB </span>","children":null,"spread":false},{"title":"common","children":[{"title":"train-labels-idx1-ubyte <span style='color:#111;'> 58.60KB </span>","children":null,"spread":false},{"title":"train-images-idx3-ubyte <span style='color:#111;'> 44.86MB </span>","children":null,"spread":false},{"title":"t10k-labels-idx1-ubyte <span style='color:#111;'> 9.77KB </span>","children":null,"spread":false},{"title":"t10k-images-idx3-ubyte <span style='color:#111;'> 7.48MB </span>","children":null,"spread":false}],"spread":true},{"title":"loadMNISTLabels.m <span style='color:#111;'> 516B </span>","children":null,"spread":false},{"title":"cnnConvolve4D.m <span style='color:#111;'> 930B </span>","children":null,"spread":false}],"spread":true},{"title":"mnist2","children":[{"title":"myCNN2.m <span style='color:#111;'> 2.72KB </span>","children":null,"spread":false},{"title":"mnist_uint8.mat <span style='color:#111;'> 14.05MB </span>","children":null,"spread":false}],"spread":true},{"title":"集成实验报告.doc <span style='color:#111;'> 34.50KB </span>","children":null,"spread":false},{"title":"cnnPool.m <span style='color:#111;'> 1.50KB </span>","children":null,"spread":false},{"title":"Mnist mycnn1 参数优化过程实验报告.doc <span style='color:#111;'> 1.11MB </span>","children":null,"spread":false},{"title":"Mnist mycnn2 参数优化过程实验报告.doc <span style='color:#111;'> 593.12KB </span>","children":null,"spread":false},{"title":"Mnist mycnn3 参数优化过程实验报告.doc <span style='color:#111;'> 673.12KB </span>","children":null,"spread":false},{"title":"mnist_uint8.mat <span style='color:#111;'> 14.05MB </span>","children":null,"spread":false},{"title":"loadMNISTLabels.m <span style='color:#111;'> 516B </span>","children":null,"spread":false},{"title":"cnnConvolve4D.m <span style='color:#111;'> 930B </span>","children":null,"spread":false},{"title":"jiceng.m <span style='color:#111;'> 3.40KB </span>","children":null,"spread":false}],"spread":false}],"spread":true}]

评论信息

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