from keras.datasets import reuters
import numpy as np
from keras.utils.np_utils import to_categorical
from keras import layers
from keras import models
import matplotlib.pyplot as plt
def vectorize_sequences(sequences,dimension = 10000):
result = np.zeros((len(sequences),dimension))
for i in range(len(sequences)):
result[i,sequences[i]] = 1
return result
#8982条训练数据,2246条测试数据
(x_train, y_train),(x_test, y_test) = reuters.load_data(num_words=10000)
#训练数据向量化
x_train = vectorize_sequences(x_train)
y_train = to_categorical(y_train) network = models.Sequential()
network.add(layers.Dense(64,activation='relu'))
network.add(layers.Dense(64,activation='relu'))
#softmax返回一个概率值,每个概率是分到该类别的可能性
network.add(layers.Dense(46,activation='softmax')) network.compile(optimizer='rmsprop',loss='categorical_crossentropy',metrics=['accuracy']) history = network.fit(x_train,y_train,batch_size=256,epochs=20,validation_split=0.25) history_dict = history.history
loss = history_dict['loss']
val_loss = history_dict['val_loss']
acc = history_dict['acc']
val_acc = history_dict['val_acc'] epochs = range(1,21)
#loss的图
plt.subplot(121)
plt.plot(epochs,loss,'g',label = 'Training loss')
plt.plot(epochs,val_loss,'b',label = 'Validation loss')
plt.xlabel('Epochs')
plt.ylabel('Loss')
#显示图例
plt.legend() plt.subplot(122)
plt.plot(epochs,acc,'g',label = 'Training accuracy')
plt.plot(epochs,val_acc,'b',label = 'Validation accuracy')
plt.xlabel('Epochs')
plt.ylabel('accuracy')
plt.legend()
plt.show()
在第9轮以后,随之模型的训练,训练集的loss不断减少,但是验证集的loss开始增加,这种情况发生了过拟合,把轮次改成9即可