博客
关于我
强烈建议你试试无所不能的chatGPT,快点击我
机器学习算法(5):卷积神经网络原理及其keras实现
阅读量:5226 次
发布时间:2019-06-14

本文共 2384 字,大约阅读时间需要 7 分钟。

1.原理

CNN的资料特别多,这里不再赘述,仅收集相关的资料供大家参考:

a.

b.

2.实现

我们使用keras实现CNN,Keras的使用文档请参考

a.

b.。

参考keras官方的例子,我们使用keras,对数据集mnist训练一个cnn模型,实现的代码如下:

'''Trains a simple convnet on the MNIST dataset.Gets to 99.25% test accuracy after 12 epochs(there is still a lot of margin for parameter tuning).16 seconds per epoch on a GRID K520 GPU.'''from __future__ import print_functionimport kerasfrom keras.datasets import mnistfrom keras.models import Sequentialfrom keras.layers import Dense, Dropout, Flattenfrom keras.layers import Conv2D, MaxPooling2Dfrom keras import backend as Kbatch_size = 128num_classes = 10epochs = 12# input image dimensionsimg_rows, img_cols = 28, 28# the data, shuffled and split between train and test sets(x_train, y_train), (x_test, y_test) = mnist.load_data()if K.image_data_format() == 'channels_first':    x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols)    x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols)    input_shape = (1, img_rows, img_cols)else:    x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1)    x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1)    input_shape = (img_rows, img_cols, 1)x_train = x_train.astype('float32')x_test = x_test.astype('float32')x_train /= 255x_test /= 255print('x_train shape:', x_train.shape)print(x_train.shape[0], 'train samples')print(x_test.shape[0], 'test samples')# convert class vectors to binary class matricesy_train = keras.utils.to_categorical(y_train, num_classes)y_test = keras.utils.to_categorical(y_test, num_classes)model = Sequential()model.add(Conv2D(32, kernel_size=(3, 3),                 activation='relu',                 input_shape=input_shape))model.add(Conv2D(64, (3, 3), activation='relu'))model.add(MaxPooling2D(pool_size=(2, 2)))model.add(Dropout(0.25))model.add(Flatten())model.add(Dense(128, activation='relu'))model.add(Dropout(0.5))model.add(Dense(num_classes, activation='softmax'))model.compile(loss=keras.losses.categorical_crossentropy,              optimizer=keras.optimizers.Adadelta(),              metrics=['accuracy'])model.fit(x_train, y_train,          batch_size=batch_size,          epochs=epochs,          verbose=1,          validation_data=(x_test, y_test))score = model.evaluate(x_test, y_test, verbose=0)print('Test loss:', score[0])print('Test accuracy:', score[1])

 

转载于:https://www.cnblogs.com/cv-pr/p/7141857.html

你可能感兴趣的文章
图像处理中双线性插值
查看>>
RobHess的SIFT代码解析之RANSAC
查看>>
03 线程池
查看>>
201771010125王瑜《面向对象程序设计(Java)》第十三周学习总结
查看>>
手机验证码执行流程
查看>>
python 基础 ----- 变量
查看>>
设计模式课程 设计模式精讲 2-2 UML类图讲解
查看>>
Silverlight 的菜单控件。(不是 Toolkit的)
查看>>
:hover 鼠标同时触发两个元素变化
查看>>
go语言学习十三 - 相等性
查看>>
Idea 提交代码到码云(提交到github也大同小异)
查看>>
c#连接excel2007未安装ISAM解决
查看>>
Mono 异步加载数据更新主线程
查看>>
初识lua
查看>>
我是插件狂人,jDuang,jValidator,jModal,jGallery
查看>>
张季跃 201771010139《面向对象程序设计(java)》第四周学习总结
查看>>
如何解除循环引用
查看>>
android中fragment的使用及与activity之间的通信
查看>>
字典【Tire 模板】
查看>>
jquery的contains方法
查看>>