keras安装完成以后,学习一个完整的小案例:电影评论分类问题
二分类问题,将电影评论划分为正面或负面
IMDB数据集内置于Keras库中,一共包含50000条严重两极分化的评论,其中25000条用于训练,25000条用于测试。且训练集和测试集都包含50%的正面评论和50%的负面评论。
import numpy as np
import matplotlib.pyplot as plt
from keras import models
from keras import layers
from keras import optimizers
from keras.datasets import imdb
#导入数据
(train_data, train_labels), (test_data, test_labels) = imdb.load_data(num_words=10000)
#将评论解码为英文
word_index = imdb.get_word_index()
reverse_word_index = dict([(value, key) for (key, value) in word_index.items()])
decoded_review = ''.join([reverse_word_index.get(i-3,'?')for i in train_data[0]])
#将整数编码为二进制矩阵
def vectorize_sequences(sequences, dimension=10000):
results=np.zeros((len(sequences),dimension))
for i, sequence in enumerate(sequences):
results[i, sequence]=1.
return results
#训练和测试数据向量化
x_train=vectorize_sequences(train_data)
x_test=vectorize_sequences(test_data)
y_train = np.asarray(train_labels).astype('float32')
y_test = np.asarray(test_labels).astype('float32')
#验证集
x_val = x_train[:10000]
partial_x_train = x_train[10000:]
y_val = y_train[:10000]
partial_y_train = y_train[10000:]
#定义模型
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'))
#训练模型
model.compile(optimizer='rmsprop', loss='binary_crossentropy', metrics=['acc'])
history = model.fit(partial_x_train, partial_y_train, epochs=20, batch_size=512, validation_data=(x_val, y_val))
#绘制训练损失和验证损失图像
history_dict = history.history
loss_values = history_dict['loss']
val_loss_values = history_dict['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()
#绘制训练精度和验证精度
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()
运行结果: