基于Keras实现CNN

短命女 2022-06-13 11:54 210阅读 0赞

## 1.前言 ##

自己定义的CNN结构，基于Keras实现，处理MNIST数据集。

## 2.Python代码 ##

加载相应库：

import numpy as np 
    np.random.seed(1337)
    from keras.datasets import mnist
    from keras.utils import np_utils
    from keras.models import Sequential
    from keras.layers import Dense,Activation,Convolution2D,MaxPooling2D,Flatten
    from keras.optimizers import Adam

定义训练、测试集：

(X_train,y_train),(X_test,y_test)=mnist.load_data()
    X_train = X_train.reshape(-1,1,28,28)
    X_test = X_test.reshape(-1,1,28,28)
    y_train = np_utils.to_categorical(y_train,num_classes=10)
    y_test = np_utils.to_categorical(y_test,num_classes=10)

定义网络结构：

model=Sequential()
    
    # Conv layer 1 output shape (32,28,28)
    model.add(Convolution2D(
    	nb_filter=32,
    	nb_row=5,
    	nb_col=5,
    	border_mode='same',    # padding method
    	input_shape=(1,28,28),
    	))
    model.add(Activation('relu'))
    
    # Pooling layer 1 (max pooling) output shape (32,14,14)
    model.add(MaxPooling2D(
    	pool_size=(2,2),
    	strides=(2,2),
    	border_mode='same',
    	))
    
    # Conv layer 2 output shape (64,14,14)
    model.add(Convolution2D(64,5,5,border_mode='same'))
    model.add(Activation('relu'))
    
    # Pooling layer 2 (max pooling) output shape (64,7,7)
    model.add(MaxPooling2D(pool_size=(2,2),border_mode='same'))
    
    
    # Fully connected layer 1 input shape (64*7*7)=(3136)
    model.add(Flatten())
    model.add(Dense(1024))
    model.add(Activation('relu'))
    
    # Fully connected layer 2 to shape (10) for 10 classes
    model.add(Dense(10))
    model.add(Activation('softmax'))
    
    adam = Adam(lr=1e-4)
    
    model.compile(optimizer=adam,
    			loss='categorical_crossentropy',
    			metrics=['accuracy'])

输出结果：

print('Training----------')
    model.fit(X_train,y_train,nb_epoch=1,batch_size=32,)
    
    print('Testing----------')
    loss,accuracy = model.evaluate(X_test,y_test)
    
    print('\ntest loss:',loss)
    print('\naccyracy:',accuracy)

## 3.结果 ##

![Center][]

[Center]: /images/20220613/361700059a6b449489a86fc7693954b7.png