keras速度复习-mnist分类

import numpy as np
from keras.datasets import mnist
from keras.utils import np_utils
from keras.models import Sequential
from keras.layers import Dense
from keras.optimizers import SGD

#load data(从网上下载数据集!)
(x_train,y_train),(x_test,y_test)=mnist.load_data()
#x_shape: (60000, 28, 28)
print('x_shape:',x_train.shape)
#y_shape: (60000,)
print('y_shape:',y_train.shape)
#x_shape: (60000, 28, 28)->x_shape: (60000, 784)
x_train=x_train.reshape(x_train.shape[0],784)/255.0#shape0就是60000,-1自动计算28*28
x_test=x_test.reshape(x_test.shape[0],784)/255.0
#换one hot格式:把输出训练成10个类
y_train=np_utils.to_categorical(y_train,num_classes=10)
y_test=np_utils.to_categorical(y_test,num_classes=10)

#创建模型:输入784个神经元,输出10个神经元
model=Sequential([
        Dense(units=10,input_dim=784,bias_initializer='one',activation='softmax')
        ])

#定义优化器
sgd=SGD(lr=0.2)

#定义优化器,loss function,训练过程中计算准确率
model.compile(
        optimizer=sgd,
        loss='mse',
        metrics=['accuracy'],
        )

#训练模型,每次训练32组数据,共需60000/32次训练,这叫一个周期,一共训练3个周期
model.fit(x_train,y_train,batch_size=32,epochs=3)

#评估模型
loss,accuracy=model.evaluate(x_test,y_test)

print('\ntest loss',loss)
print('accuracy',accuracy)



补充:优化器定义时可以使用交叉熵代价函数categorical_crossentropy
model.compile(
        optimizer=sgd,
        loss='categorical_crossentropy',
        metrics=['accuracy'],
        )

激活函数

sigmoid     

softmax    

 

交叉熵损失函数

keras速度复习-mnist分类_第1张图片

你可能感兴趣的:(机器学习(MOOC笔记代码))