keras 实现CNN 进行手写字符识别

转载的博客：http://machinelearningmastery.com/handwritten-digit-recognition-using-convolutional-neural-networks-python-keras/

1、显示设置输入张量的维度

from keras import backend as K
K.set_image_dim_ordering('th')

2、准备数据,格式转换

#load data
(X_train,y_train),(X_test,y_test) = mnist.load_data()

#reshape to be [samples][pixels][width][height]
X_train = X_train.reshape(X_train.shape[0],1,28,28).astype('float32')
X_test = X_test.reshape(X_test.shape[0],1,28,28).astype('float32')
X_train = X_train/255
X_test = X_test/255

#one hot encode
y_train = np_utils.to_categorical(y_train)
y_test = np_utils.to_categorical(y_test)
num_classes = y_test.shape[1]

3、定义模型,dropout可以在最后一层的max pooling之后

def baseline_model():
    #create model
    model = Sequential()
    model.add(Convolution2D(30,5,5,border_mode='valid',input_shape=(1,28,28),activation='relu'))
    model.add(MaxPooling2D(pool_size=(2,2)))
    model.add(Convolution2D(15,3,3,activation='relu'))
    model.add(MaxPooling2D(pool_size=(2,2)))
    model.add(Dropout(0.2))
    model.add(Flatten())
    model.add(Dense(128,activation='relu'))
    model.add(Dense(50,activation='relu'))
    model.add(Dense(num_classes,activation='softmax'))
    #Compile model
    model.compile(loss='categorical_crossentropy',optimizer='adam',metrics=['accuracy'])
    return model

4、训练模型

model = baseline_model()
model.fit(X_train,y_train,validation_data=(X_test,y_test),nb_epoch=10,batch_size=200,verbose=2)
#
scores = model.evaluate(X_test,y_test,verbose=0)
print("Baseline Error: %.2f%%" % (100-scores[1]*100))

5、完整代码如下：

import numpy
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import Dropout
from keras.layers import Flatten
from keras.layers.convolutional import Convolution2D
from keras.layers.convolutional import MaxPooling2D
from keras.utils import np_utils
from keras import backend as K
K.set_image_dim_ordering('th')

seed = 7
numpy.random.seed(seed)

#load data
(X_train,y_train),(X_test,y_test) = mnist.load_data()

#reshape to be [samples][pixels][width][height]
X_train = X_train.reshape(X_train.shape[0],1,28,28).astype('float32')
X_test = X_test.reshape(X_test.shape[0],1,28,28).astype('float32')
X_train = X_train/255
X_test = X_test/255

#one hot encode
y_train = np_utils.to_categorical(y_train)
y_test = np_utils.to_categorical(y_test)
num_classes = y_test.shape[1]

def baseline_model():
    #create model
    model = Sequential()
    model.add(Convolution2D(30,5,5,border_mode='valid',input_shape=(1,28,28),activation='relu'))
    model.add(MaxPooling2D(pool_size=(2,2)))
    model.add(Convolution2D(15,3,3,activation='relu'))
    model.add(MaxPooling2D(pool_size=(2,2)))
    model.add(Dropout(0.2))
    model.add(Flatten())
    model.add(Dense(128,activation='relu'))
    model.add(Dense(50,activation='relu'))
    model.add(Dense(num_classes,activation='softmax'))
    #Compile model
    model.compile(loss='categorical_crossentropy',optimizer='adam',metrics=['accuracy'])
    return model


model = baseline_model()
model.fit(X_train,y_train,validation_data=(X_test,y_test),nb_epoch=10,batch_size=200,verbose=2)
#
scores = model.evaluate(X_test,y_test,verbose=0)
print("Baseline Error: %.2f%%" % (100-scores[1]*100))