Keras对CIFAR10的图像分类全套代码(包含多个模型)

上传者: 45508265 | 上传时间: 2022-05-17 17:08:42 | 文件大小: 557.36MB | 文件类型: ZIP
利用tensorflow的后端Keras实现我们的CIFAR10的图像分类 keras简单易懂,代码量和工程都不大,可以自动利用GPU进行训练,调节显存的大小 模型有LeNet,AlexNet,VGG,GoogLeNet,ResNet,DenseNet等等 也可以通过进行可视化输出结果,也含有数据增强等方法提高准确率 在资源中有全部代码的学习资料,并且包括所有的权重,代码所有都可运行,可执行,可复现代码的结果 可以利用所有的模型权重进行迁移学习,利用自己的数据集进行运行得到结果都是可以的

文件下载

资源详情

[{"title":"( 42 个子文件 557.36MB ) Keras对CIFAR10的图像分类全套代码(包含多个模型)","children":[{"title":"Keras-Image-Classification","children":[{"title":"Keras CIFAR-10分类(SVM 分类器).ipynb <span style='color:#111;'> 130.08KB </span>","children":null,"spread":false},{"title":"Keras CIFAR-10分类(LeNet5).ipynb <span style='color:#111;'> 298.95KB </span>","children":null,"spread":false},{"title":"Keras CIFAR-10分类(GoogleNet).ipynb <span style='color:#111;'> 441.33KB </span>","children":null,"spread":false},{"title":"Keras CIFAR-10分类(ResNet).ipynb <span style='color:#111;'> 325.32KB </span>","children":null,"spread":false},{"title":"Keras CIFAR-10分类(ResNeXt).ipynb <span style='color:#111;'> 529.45KB </span>","children":null,"spread":false},{"title":"Keras CIFAR-10分类(VGG16).ipynb <span style='color:#111;'> 241.16KB </span>","children":null,"spread":false},{"title":"Keras CIFAR-10分类(DenseNet).ipynb <span style='color:#111;'> 364.61KB </span>","children":null,"spread":false},{"title":"Keras CIFAR-10分类(AlexNet).ipynb <span style='color:#111;'> 304.28KB </span>","children":null,"spread":false},{"title":"Keras CIFAR-10分类(自定义simple CNN).ipynb <span style='color:#111;'> 255.30KB </span>","children":null,"spread":false}],"spread":true},{"title":"output","children":[{"title":"predict_alexnet.png <span style='color:#111;'> 89.12KB </span>","children":null,"spread":false},{"title":"best_lenet5_simple.h5 <span style='color:#111;'> 780.36KB </span>","children":null,"spread":false},{"title":"keras_cifar10_googleNet_model.h5 <span style='color:#111;'> 69.20MB </span>","children":null,"spread":false},{"title":"keras_cifar10_complex_cnn_model.h5 <span style='color:#111;'> 96.27MB </span>","children":null,"spread":false},{"title":"predict_googleNet.png <span style='color:#111;'> 92.20KB </span>","children":null,"spread":false},{"title":"best_densenet_simple.h5 <span style='color:#111;'> 11.85MB </span>","children":null,"spread":false},{"title":"predict_complex_cnn.png <span style='color:#111;'> 92.63KB </span>","children":null,"spread":false},{"title":"best_alexnet_simple.h5 <span style='color:#111;'> 110.38MB </span>","children":null,"spread":false},{"title":"keras_cifar10_alexnet_model.h5 <span style='color:#111;'> 110.38MB </span>","children":null,"spread":false},{"title":"best_googleNet_simple.h5 <span style='color:#111;'> 69.20MB </span>","children":null,"spread":false},{"title":"cifar10_svm.png <span style='color:#111;'> 10.97KB </span>","children":null,"spread":false},{"title":"best_resnext_simple.h5 <span style='color:#111;'> 3.94MB </span>","children":null,"spread":false},{"title":"cifar10_resnext.png <span style='color:#111;'> 2.53MB </span>","children":null,"spread":false},{"title":"predict_resnet.png <span style='color:#111;'> 90.87KB </span>","children":null,"spread":false},{"title":"cifar10_resnet.png <span style='color:#111;'> 1.06MB </span>","children":null,"spread":false},{"title":"best_resnet_simple.h5 <span style='color:#111;'> 5.90MB </span>","children":null,"spread":false},{"title":"predict_lenet5.png <span style='color:#111;'> 90.54KB </span>","children":null,"spread":false},{"title":"keras_cifar10_svm_model.h5 <span style='color:#111;'> 379.09KB </span>","children":null,"spread":false},{"title":"keras_cifar10_densenet_model.h5 <span style='color:#111;'> 11.85MB </span>","children":null,"spread":false},{"title":"predict_densenet.png <span style='color:#111;'> 89.68KB </span>","children":null,"spread":false},{"title":"cifar10_densenet.png <span style='color:#111;'> 4.91MB </span>","children":null,"spread":false},{"title":"best_complex_cnn_simple.h5 <span style='color:#111;'> 96.27MB </span>","children":null,"spread":false},{"title":"keras_cifar10_resnext_model.h5 <span style='color:#111;'> 5.25MB </span>","children":null,"spread":false},{"title":"best_svm_simple.h5 <span style='color:#111;'> 379.09KB </span>","children":null,"spread":false},{"title":"keras_cifar10_lenet5_model.h5 <span style='color:#111;'> 780.36KB </span>","children":null,"spread":false},{"title":"cifar10_googleNet.png <span style='color:#111;'> 1.21MB </span>","children":null,"spread":false},{"title":"cifar10_lenet5.png <span style='color:#111;'> 81.73KB </span>","children":null,"spread":false},{"title":"best_resnet_data_augmentation.h5 <span style='color:#111;'> 4.09MB </span>","children":null,"spread":false},{"title":"keras_cifar10_resnet_model.h5 <span style='color:#111;'> 5.90MB </span>","children":null,"spread":false},{"title":"best_simple_cnn_simple.h5 <span style='color:#111;'> 718.85KB </span>","children":null,"spread":false},{"title":"predict_resnext.png <span style='color:#111;'> 90.58KB </span>","children":null,"spread":false},{"title":"cifar10_alexnet.png <span style='color:#111;'> 157.60KB </span>","children":null,"spread":false},{"title":"cifar10_simple_cnn.png <span style='color:#111;'> 68.64KB </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