例子---电影评论二分类

# 加载IMDB数据集
from keras.datasets import imdb
import numpy as np

'''预处理'''
# num_words表示仅保留训练数据中前5个最常见的单词
# train_data是评论组成的列表，train_data[0]=[1,2,3],train_labels[0]=1
(train_data,train_labels),(test_data,test_labels) = imdb.load_data(num_words=5)

# 将整数序列编码为二进制矩阵
def vectorize_sequences(sequences,dimension=5):
	results = np.zeros((len(sequences),dimension)) # 形状(len(sequences),dimension)
	for i,sequence in enumerate(sequences):
		results[i,sequence] = 1.
	return results
# x_train[0] = array([0., 1., 1., 1., 0.])
x_train = vectorize_sequences(train_data)
x_test = vectorize_sequences(test_data)

# 标签向量化
y_train = np.asarray(train_labels).astype('float32')
y_test = np.asarray(test_labels).astype('float32')

'''构建网络'''
from keras import models
from keras import layers

model = models.Sequential()
model.add(layers.Dense(16,activation='relu',input_shape=(10000,)))
model.add(layers.Dense(16,activation='relu'))
model.add(layers.Dense(1,activation='sigmoid'))
model.compile(optimizer='rmsprop',loss='binary_crossentropy',metrics=['accuracy'])

'''验证集'''
x_val = x_train[:10000]
partial_x_train = [x_train[10000:]

y_val = y_train[:10000]
partial_y_train = [x_train[10000:]
'''先画图寻找最佳epochs,改变超参数寻找最佳损失值与精度'''
# model.fit(x_train,y_train,epochs=4,batch_size=512)
# results = model.evaluate(x_test,y_test)
## results == [loss, accuracy] == [0.29299, 0.8832799]

# 获取测试集预测结果
# model.predict(x_test)
## == array([[0.9800627] [0.99758697] ... ], dtype=float32)

'''再画图寻找最佳epochs'''
# 观察验证/训练精度随epoch变化的性能影响，取验证精度最高的epochs
history = model.fit(partial_x_train,partial_y_train,epochs=20,batch_size=512,validation_data=(x_val,y_val))
# history_dict = history.history
# history_dict.keys()
# == dict_keys(['val_acc','acc','val_loss','loss'])

'''绘制训练损失'''
import matplotlib.pyplot as plt
history_dict = history.history
loss = history.history['loss']
val_acc = history.history['val_acc']
loss_values = history.history['loss']
val_loss_values = history.history['val_loss']

epochs = range(1, len(loss_values)+1)

plt.plot(epochs, loss_values, 'bo', label='Training loss')
plt.plot(epochs, val_loss_values, 'b', label='Validation loss')
plt.title('Training and validation loss')
plt.xlabel('Epochs')
plt.ylabel('Loss')
plt.legend()
plt.show()


'''绘制验证精度'''
plt.clf() # 清空图像
acc = history_dict['acc']
val_acc = history_dict['val_acc']

plt.plot(epochs, acc, 'bo', label='Training acc')
plt.plot(epochs, val_acc, 'b', label='Validation acc')
plt.title('Training and validation accuracy')
plt.xlabel('Epochs')
plt.ylabel('Accuracy')
plt.legend()
plt.show()