import numpy as np
from keras.datasets import mnist #MNIST数据集
from keras.utils import np_utils
from keras.models import Sequential
from keras.layers import Dense
from keras.optimizers import SGD
#载入数据
(x_train,y_train),(x_test,y_test) = mnist.load_data()
#(60000,28,28)
print('x_shape',x_train.shape)
#(60000)
print('y_shape',y_train.shape)
#(60000,28,28)->(60000,784)
x_train = x_train.reshape(x_train.shape[0],-1)/255.0
#-1可以自动转换成合适的列数,经转换后就可以转换为60000行,784列。
x_test = x_test.reshape(x_test.shape[0],-1)/255.0
#除以255是为了归一化
#转 one hot格式
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')
]) #bias_initializer 偏置值
#定义优化器,loss function,训练过程中计算准确率
sgd = SGD(lr=0.2) #学习率为0.2
model.compile(
optimizer = sgd,
loss = 'mse',
metrics=['accuracy'], #准确率
)
#训练数据集
model.fit(x_train,y_train,batch_size=32,epochs=10)#每个batch都有32张图片,epochs是训练周期,数据集中有60000张图片,每次取32张图片训练,60000张全部取完为循环一次
#评估模型
loss,accuracy = model.evaluate(x_test,y_test)
print('\ntest loss',loss)
print('accuracy',accuracy)
模型层数太少,因此训练结果不是很准确,下面进行改进。
使用Dropout
增加模型层数可以提升模型的准确率
如果数据量过大,则应该使用dropout这种方法,否则很容易产生过拟合的现象,影响测试集的准确率
训练集和测试集的准确率差距可能会非常大
import numpy as np
from keras.datasets import mnist #MNIST数据集
from keras.utils import np_utils
from keras.models import Sequential
from keras.layers import Dense,Dropout #这个地方改了!!!导入Dropout!!!
from keras.optimizers import SGD
#载入数据
(x_train,y_train),(x_test,y_test) = mnist.load_data()
#(60000,28,28)
print('x_shape',x_train.shape)
#(60000)
print('y_shape',y_train.shape)
#(60000,28,28)->(60000,784)
x_train = x_train.reshape(x_train.shape[0],-1)/255.0 #-1可以自动转换成合适的列数,经转换后就可以转换为60000行,784列。
x_test = x_test.reshape(x_test.shape[0],-1)/255.0 #除以255是为了归一化
#转 one hot格式
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
#下面这个地方也改了,加了隐藏层!!!!!!!!!!!!!可以在创建的时候就加一层,也可以像之前的时候那样在下面add(dense(...))
#注意层与层之间要加‘,’隔开
model = Sequential([
Dense(units=200,input_dim=784,bias_initializer='one',activation='tanh'),
Dropout(0.4),#这里设置0.4可以使40%的神经元不工作
Dense(units=100,bias_initializer='one',activation='tanh'),
Dropout(0.4),
Dense(units=10,bias_initializer='one',activation='softmax')
]) #bias_initializer 偏置值
#定义优化器,loss function,训练过程中计算准确率
sgd = SGD(lr=0.2) #学习率为0.2
model.compile(
optimizer = sgd,
loss = 'categorical_crossentropy',
metrics=['accuracy'], #准确率
)
#训练数据集
model.fit(x_train,y_train,batch_size=32,epochs=10)#每个batch都有32张图片,epochs是训练周期,数据集中有60000张图片,每次取32张图片训练,60000张全部取完为循环一次
#评估模型
loss,accuracy = model.evaluate(x_test,y_test)
print('\ntest loss',loss)
print('accuracy',accuracy)
loss,accuracy = model.evaluate(x_train,y_train)
print('\ntrain loss',loss)
print('train accuracy',accuracy)