机器学习大作业线性回归模型和卷积模型识别数字手写体.zip

上传者: 55305220 | 上传时间: 2022-11-21 20:25:52 | 文件大小: 22.7MB | 文件类型: ZIP
机器学习大作业线性回归模型和卷积模型识别数字手写体.zip使用TensorFlow技术和Flask框架相结合,采用MNIST数据集作为数据,通过前端HTML和jQuery框架,利用canvas画布将用户在屏幕上的手写文字传入到后台Flask的Restful API中,然后flask通过调取模型接口,把数据传入模型中进行手写体识别,形成一个完整的闭环。本文使用两种方法训练数据,线性和卷积的方法,并将结果进行对比。训练结果较为理想,可以有效识别出手写数字,并得到较好的准确率。 本次MNIST手写数字识别首先使用MNIST来导入数据,建立模型,建立了线性模型和卷积模型。再通过调取模型,进行训练,建立训练模型,保存参数模型,得到训练模型。通过前端请求,加载模型,进行调用。完成数据传入,训练,打包,调用。可以作为基础,可以通过相关数据集训练进行更多图像分类。

文件下载

资源详情

[{"title":"( 26 个子文件 22.7MB ) 机器学习大作业线性回归模型和卷积模型识别数字手写体.zip","children":[{"title":"Homework_MachineLearning-master","children":[{"title":"main.py <span style='color:#111;'> 1.31KB </span>","children":null,"spread":false},{"title":"mnist","children":[{"title":"input_data.py <span style='color:#111;'> 326B </span>","children":null,"spread":false},{"title":"regression.py <span style='color:#111;'> 1.28KB </span>","children":null,"spread":false},{"title":"data","children":[{"title":"regression.ckpt.index <span style='color:#111;'> 162B </span>","children":null,"spread":false},{"title":"regression.ckpt.data-00000-of-00001 <span style='color:#111;'> 30.66KB </span>","children":null,"spread":false},{"title":"convalutional.ckpt.data-00000-of-00001 <span style='color:#111;'> 12.49MB </span>","children":null,"spread":false},{"title":"convalutional.ckpt.index <span style='color:#111;'> 353B </span>","children":null,"spread":false}],"spread":true},{"title":"convolutional.py <span style='color:#111;'> 1.60KB </span>","children":null,"spread":false},{"title":"__pycache__","children":[{"title":"input_data.cpython-36.pyc <span style='color:#111;'> 550B </span>","children":null,"spread":false},{"title":"input_data.cpython-310.pyc <span style='color:#111;'> 631B </span>","children":null,"spread":false},{"title":"__init__.cpython-36.pyc <span style='color:#111;'> 189B </span>","children":null,"spread":false},{"title":"model.cpython-36.pyc <span style='color:#111;'> 1.95KB </span>","children":null,"spread":false}],"spread":true},{"title":"__init__.py <span style='color:#111;'> 40B </span>","children":null,"spread":false},{"title":"model.py <span style='color:#111;'> 1.63KB </span>","children":null,"spread":false},{"title":"MNIST_data","children":[{"title":"t10k-images-idx3-ubyte.gz <span style='color:#111;'> 1.57MB </span>","children":null,"spread":false},{"title":"t10k-labels-idx1-ubyte.gz <span style='color:#111;'> 4.44KB </span>","children":null,"spread":false},{"title":"train-labels-idx1-ubyte.gz <span style='color:#111;'> 28.20KB </span>","children":null,"spread":false},{"title":"train-images-idx3-ubyte.gz <span style='color:#111;'> 9.45MB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"templates","children":[{"title":"index.html <span style='color:#111;'> 2.76KB </span>","children":null,"spread":false}],"spread":true},{"title":"__pycache__","children":[{"title":"main.cpython-36.pyc <span style='color:#111;'> 1.64KB </span>","children":null,"spread":false}],"spread":true},{"title":".DS_Store <span style='color:#111;'> 6.00KB </span>","children":null,"spread":false},{"title":"static","children":[{"title":"css","children":[{"title":"bootstrap.min.css <span style='color:#111;'> 55B </span>","children":null,"spread":false}],"spread":true},{"title":"js","children":[{"title":"jquery.min.js <span style='color:#111;'> 44B </span>","children":null,"spread":false},{"title":"main.js <span style='color:#111;'> 18.96KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"src","children":[{"title":"js","children":[{"title":"main.js <span style='color:#111;'> 4.71KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"使用教程.txt <span style='color:#111;'> 926B </span>","children":null,"spread":false}],"spread":true}],"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