使用keras实现手写数字辨识

导包

import numpy as np
from keras.models import Sequential
from keras.layers.core import Dense,Dropout,Activation
from keras.optimizers import SGD,Adam
from keras.utils import np_utils
from keras.datasets import mnist

载入数据

def load_data():
    (x_train,y_train),(x_test,y_test)=mnist.load_data()
    number=10000
    x_train=x_train[0:number]
    y_train=y_train[0:number]
    x_train=x_train.reshape(number,28*28)
    x_test=x_test.reshape(x_test.shape[0],28*28)
    x_train=x_train.astype('float32')
    x_test=x_test.astype('float32')
    y_train=np_utils.to_categorical(y_train,10)
    y_test=np_utils.to_categorical(y_test,10)
    x_train=x_train
    x_test=x_test
    x_train=x_train/255
    x_test=x_test/255
    return (x_train,y_train),(x_test,y_test)

构建一个全连接神经网络

model = Sequential()
      model.add(Dense(input_dim=28 * 28, units=689, activation='relu'))
      model.add(Dropout(0.7))
      model.add(Dense(units=689, activation='relu'))
      model.add(Dropout(0.7))
      model.add(Dense(units=689, activation='relu'))
      model.add(Dropout(0.7))
      model.add(Dense(units=10, activation='softmax'))

loss fuction

model.compile(loss='categorical_crossentropy',
                    optimizer='Adam',
                    metrics=['accuracy'])

完整代码

import numpy as np
from keras.models import Sequential
from keras.layers.core import Dense,Dropout,Activation
from keras.optimizers import SGD,Adam
from keras.utils import np_utils
from keras.datasets import mnist

def load_data():
    (x_train,y_train),(x_test,y_test)=mnist.load_data()
    number=10000
    x_train=x_train[0:number]
    y_train=y_train[0:number]
    x_train=x_train.reshape(number,28*28)
    x_test=x_test.reshape(x_test.shape[0],28*28)
    x_train=x_train.astype('float32')
    x_test=x_test.astype('float32')
    y_train=np_utils.to_categorical(y_train,10)
    y_test=np_utils.to_categorical(y_test,10)
    x_train=x_train
    x_test=x_test
    x_train=x_train/255
    x_test=x_test/255
    return (x_train,y_train),(x_test,y_test)


  if __name__ == '__main__':
      ##load training data and testing data

      (x_train, y_train), (x_test, y_test) = load_data()
      ## 1、define a set of function--neural network
      model = Sequential()
      model.add(Dense(input_dim=28 * 28, units=689, activation='relu'))
      model.add(Dropout(0.7))
      model.add(Dense(units=689, activation='relu'))
      model.add(Dropout(0.7))
      model.add(Dense(units=689, activation='relu'))
      model.add(Dropout(0.7))
      model.add(Dense(units=10, activation='softmax'))

      model.compile(loss='categorical_crossentropy',
                    optimizer='Adam',
                    metrics=['accuracy'])
      ##train data
      model.fit(x_train, y_train, batch_size=100, epochs=20)


      # evaluate the model and out put the accuracy
      result = model.evaluate(x_train, y_train, batch_size=10000)
      print('Train ACC:', result[1])
      result = model.evaluate(x_test, y_test, batch_size=10000)
      print('Test ACC:', result[1])