入门项目数字手写体识别：使用Keras完成CNN模型搭建

#源代码不能直接下载，在这里进行稍微修改，下载数据集后指定路径#下载链接：https://pan.baidu.com/s/1jH6uFFC 密码: dw3dfrom __future__ import print_functionimport kerasimport numpy as np  
path='./mnist.npz'  f = np.load(path)
X_train, y_train = f['x_train'], f['y_train']  
X_test, y_test = f['x_test'], f['y_test'] 

import matplotlib.pyplot as plt
fig = plt.figure()for i in range(9):
 plt.subplot(3,3,i+1)
 plt.tight_layout()
 plt.imshow(X_train[i], cmap='gray', interpolation='none')
 plt.title("Digit: {}".format(y_train[i]))
 plt.xticks([])
 plt.yticks([])
fig

# let's print the actual data shape before we reshape and normalizeprint("X_train shape", X_train.shape)print("y_train shape", y_train.shape)print("X_test shape", X_test.shape)print("y_test shape", y_test.shape)#input image size 28*28img_rows , img_cols = 28, 28#reshaping#"channels_first" assumes (channels, conv_dim1, conv_dim2, conv_dim3).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)#more reshapingX_train = X_train.astype('float32')
X_test = X_test.astype('float32')
X_train /= 255
X_test /= 255print('X_train shape:', X_train.shape) #X_train shape: (60000, 28, 28, 1)

import keras#set number of categoriesnum_category = 10# convert class vectors to binary class matricesy_train = keras.utils.to_categorical(y_train, num_category)
y_test = keras.utils.to_categorical(y_test, num_category)

#导入相关层的结构from __future__ import print_functionimport kerasfrom keras.datasets import mnistfrom keras.models import Sequentialfrom keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPooling2Dfrom keras import backend as kimport matplotlib.pyplot as pltimport numpy as np## model buildingmodel = Sequential()#convolutional layer with rectified linear unit activationmodel.add(Conv2D(32, kernel_size=(3, 3),
                activation='relu',
                input_shape=input_shape))#32 convolution filters used each of size 3x3#againmodel.add(Conv2D(64, (3, 3), activation='relu'))#64 convolution filters used each of size 3x3#choose the best features via poolingmodel.add(MaxPooling2D(pool_size=(2, 2)))#randomly turn neurons on and off to improve convergencemodel.add(Dropout(0.25))#flatten since too many dimensions, we only want a classification outputmodel.add(Flatten())#fully connected to get all relevant datamodel.add(Dense(128, activation='relu'))#one more dropout for convergence' sake :) model.add(Dropout(0.5))#output a softmax to squash the matrix into output probabilitiesmodel.add(Dense(num_category, activation='softmax'))

#Adaptive learning rate (adaDelta) is a popular form of gradient descent rivaled only by adam and adagrad#categorical ce since we have multiple classes (10) model.compile(loss=keras.losses.categorical_crossentropy,
             optimizer=keras.optimizers.Adadelta(),
             metrics=['accuracy'])

batch_size = 128
num_epoch = 10#model trainingmodel_log = model.fit(X_train, y_train,
         batch_size=batch_size,
         epochs=num_epoch,
         verbose=1,
         validation_data=(X_test, y_test))

score = model.evaluate(X_test, y_test, verbose=0)print('Test loss:', score[0]) #Test loss: 0.0296396646054print('Test accuracy:', score[1]) #Test accuracy: 0.9904

#Save the model# serialize model to JSONmodel_digit_json = model.to_json()with open("model_digit.json", "w") as json_file:
   json_file.write(model_digit_json)# serialize weights to HDF5model.save_weights("model_digit.h5")
print("Saved model to disk")