全连接神经网络实现Fashion-MNIST数据集图像分类(可运行).zip

上传者: 44625365 | 上传时间: 2021-08-24 09:23:16 | 文件大小: 66.51MB | 文件类型: ZIP
是我大作业的代码了哈哈,要是需要带注释的可以私聊哈哈 代码使用方法: 1. 读取数据集 2. 初始化模型参数(选择哪个模型就初始化哪个) 3.定义激活函数(只有选择带隐含层的模型才需要激活函数) 4.防止过拟合(只有选择带隐含层的模型才需要防止过拟合,不过因为下面我们用的权重衰减在训练是也有定义,所以我们需要也给它加个定义) 5.定义模型(选择哪个模型就定义哪个) 6.定义损失函数 7. 定义优化函数 8.训练模型(训练结束可进行绘图) 9. 进行预测 可变参数: 1.选择模型(三种模型,可选用) 2.激活函数(两种) 3.防止过拟合(两种方法,可选用也可都用) 权重衰减(通过lambd 来调整, lambd = 0 即不使用此方法) 丢弃法(通过定义模型时选择) 4.损失函数(咱们的代码只用了一种) 5.优化方法(咱们的代码只用了一种) 6.训练模型(迭代周期数num_epochs和学习率lr可调) 7.定义数据集时小批量的大小

文件下载

资源详情

[{"title":"( 37 个子文件 66.51MB ) 全连接神经网络实现Fashion-MNIST数据集图像分类(可运行).zip","children":[{"title":"全连接神经网络实现Fashion-MNIST数据集图像分类","children":[{"title":"features","children":[{"title":"layer_3.jpg <span style='color:#111;'> 502B </span>","children":null,"spread":false},{"title":"layer_4.jpg <span style='color:#111;'> 386B </span>","children":null,"spread":false},{"title":"layer_2.jpg <span style='color:#111;'> 541B </span>","children":null,"spread":false},{"title":"layer_1.jpg <span style='color:#111;'> 931B </span>","children":null,"spread":false}],"spread":true},{"title":"runs","children":[{"title":"Jun25_07-48-19_DESKTOP-NLQ17LS","children":[{"title":"loss","children":[{"title":"val_loss","children":[{"title":"events.out.tfevents.1624578540.DESKTOP-NLQ17LS <span style='color:#111;'> 122B </span>","children":null,"spread":false}],"spread":true},{"title":"train_loss","children":[{"title":"events.out.tfevents.1624578540.DESKTOP-NLQ17LS <span style='color:#111;'> 122B </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"events.out.tfevents.1624578499.DESKTOP-NLQ17LS <span style='color:#111;'> 138B </span>","children":null,"spread":false}],"spread":true},{"title":"Jun25_07-52-54_DESKTOP-NLQ17LS","children":[{"title":"events.out.tfevents.1624581444.DESKTOP-NLQ17LS <span style='color:#111;'> 20.57KB </span>","children":null,"spread":false},{"title":"loss","children":[{"title":"val_loss","children":[{"title":"events.out.tfevents.1624578809.DESKTOP-NLQ17LS <span style='color:#111;'> 458B </span>","children":null,"spread":false}],"spread":true},{"title":"train_loss","children":[{"title":"events.out.tfevents.1624578809.DESKTOP-NLQ17LS <span style='color:#111;'> 458B </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"events.out.tfevents.1624578774.DESKTOP-NLQ17LS <span style='color:#111;'> 21.06KB </span>","children":null,"spread":false},{"title":"events.out.tfevents.1624581457.DESKTOP-NLQ17LS <span style='color:#111;'> 20.57KB </span>","children":null,"spread":false}],"spread":true},{"title":"Jun24_21-59-44_DESKTOP-NLQ17LS","children":[{"title":"events.out.tfevents.1624543184.DESKTOP-NLQ17LS <span style='color:#111;'> 88B </span>","children":null,"spread":false},{"title":"loss","children":[{"title":"val_loss","children":[{"title":"events.out.tfevents.1624543247.DESKTOP-NLQ17LS <span style='color:#111;'> 0B </span>","children":null,"spread":false}],"spread":true},{"title":"train_loss","children":[{"title":"events.out.tfevents.1624543247.DESKTOP-NLQ17LS <span style='color:#111;'> 0B </span>","children":null,"spread":false}],"spread":true}],"spread":true}],"spread":true},{"title":"Jun24_21-53-30_DESKTOP-NLQ17LS","children":[{"title":"events.out.tfevents.1624542810.DESKTOP-NLQ17LS <span style='color:#111;'> 88B </span>","children":null,"spread":false},{"title":"loss","children":[{"title":"val_loss","children":[{"title":"events.out.tfevents.1624542886.DESKTOP-NLQ17LS <span style='color:#111;'> 122B </span>","children":null,"spread":false}],"spread":true},{"title":"train_loss","children":[{"title":"events.out.tfevents.1624542886.DESKTOP-NLQ17LS <span style='color:#111;'> 122B </span>","children":null,"spread":false}],"spread":true}],"spread":true}],"spread":true}],"spread":true},{"title":"带注释-全连接神经网络实现Fashion-MNIST数据集图像分类.ipynb <span style='color:#111;'> 359.67KB </span>","children":null,"spread":false},{"title":"纯代码-全连接神经网络实现Fashion-MNIST数据集图像分类1.ipynb <span style='color:#111;'> 168.61KB </span>","children":null,"spread":false},{"title":"__pycache__","children":[{"title":"OurModels.cpython-36.pyc <span style='color:#111;'> 3.74KB </span>","children":null,"spread":false},{"title":"helpers.cpython-36.pyc <span style='color:#111;'> 4.81KB </span>","children":null,"spread":false}],"spread":true},{"title":"output","children":[{"title":"CNN.pt <span style='color:#111;'> 7.43MB </span>","children":null,"spread":false}],"spread":true},{"title":"dataset","children":[{"title":"FashionMNIST","children":[{"title":"raw","children":[{"title":"t10k-images-idx3-ubyte.gz <span style='color:#111;'> 4.22MB </span>","children":null,"spread":false},{"title":"t10k-labels-idx1-ubyte <span style='color:#111;'> 9.77KB </span>","children":null,"spread":false},{"title":"t10k-labels-idx1-ubyte.gz <span style='color:#111;'> 5.03KB </span>","children":null,"spread":false},{"title":"train-labels-idx1-ubyte.gz <span style='color:#111;'> 28.82KB </span>","children":null,"spread":false},{"title":"train-images-idx3-ubyte <span style='color:#111;'> 44.86MB </span>","children":null,"spread":false},{"title":"train-images-idx3-ubyte.gz <span style='color:#111;'> 25.20MB </span>","children":null,"spread":false},{"title":"t10k-images-idx3-ubyte <span style='color:#111;'> 7.48MB </span>","children":null,"spread":false},{"title":"train-labels-idx1-ubyte <span style='color:#111;'> 58.60KB </span>","children":null,"spread":false}],"spread":true}],"spread":true}],"spread":true},{"title":".ipynb_checkpoints","children":[{"title":"deep_learning-checkpoint.ipynb <span style='color:#111;'> 117.42KB </span>","children":null,"spread":false},{"title":"全连接神经网络实现Fashion-MNIST数据集图像分类-checkpoint.ipynb <span style='color:#111;'> 339.48KB </span>","children":null,"spread":false},{"title":"deep_learning-Copy1-checkpoint.ipynb <span style='color:#111;'> 29.05KB </span>","children":null,"spread":false},{"title":"softmax-checkpoint.ipynb <span style='color:#111;'> 100.12KB </span>","children":null,"spread":false},{"title":"Untitled1-checkpoint.ipynb <span style='color:#111;'> 72B </span>","children":null,"spread":false},{"title":"MLP(一层隐含层)-checkpoint.ipynb <span style='color:#111;'> 119.93KB </span>","children":null,"spread":false}],"spread":true}],"spread":true}],"spread":true}]

评论信息

  • qq_41850587 :
    用户下载后在一定时间内未进行评价,系统默认好评。
    2021-11-28
  • L_Ferris :
    具体用的什么环境做的项目
    2021-11-25
  • weixin_45787925 :
    用户下载后在一定时间内未进行评价,系统默认好评。
    2021-11-07
  • qq_45788043 :
    用户下载后在一定时间内未进行评价,系统默认好评。
    2021-11-06

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