主页

索引

模块索引

搜索页面

二分类问题

# 1. 导入数据
from keras.datasets import imdb
(train_data, train_labels), (test_data, test_labels) = imdb.load_data(num_words=10000)

# 2. 查看数据概况
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]])

# 3. 把数据转为vector类型
import numpy as np
def vectorize_sequences(sequences, dimension=10000):
    results = np.zeros((len(sequences), dimension))
    for i, sequence in enumerate(sequences):
        results[i, sequence] = 1.
    return results
x_train = vectorize_sequences(train_data)
x_test = vectorize_sequences(test_data)

# 4. label数据从int转为float列表类型
y_train = np.asarray(train_labels).astype('float32')
y_test = np.asarray(test_labels).astype('float32')


# 5. 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(16, activation='relu'))
model.add(layers.Dense(1, activation='sigmoid'))

# 6. 留出验证集
x_val = x_train[:10000]
partial_x_train = x_train[10000:]
y_val = y_train[:10000]
partial_y_train = y_train[10000:]

# 7. 解决jupyter运行keras不可用问题
import os
os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE"

# 8. 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))

# 9. 绘制训练损失和验证损失
import matplotlib.pyplot as plt
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()

# 10. 绘制训练精度和验证精度
plt.clf()
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('Loss')
plt.legend()
plt.show()

# 11. 从头开始重新训练一个模型(不需要验证集了)
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'])
model.fit(x_train, y_train, epochs=4, batch_size=512) 

# 12. 在测试数据上评估模型
results = model.evaluate(x_test, y_test)

# 13. 使用训练好的网络在新数据上生成预测结果
model.predict(x_test)

# 14. 进一步的实验
  # a. 隐藏层
  # b. 隐藏单元
  # c. 损失函数
  # d. 激活函数

# 15. 小结
  # a. 需要对原始数据做大量处理
  # b. 使用带relu的激活Dense层堆叠
  # c. 最后一层只有一个单元&使用sigmod激活
  # d. 使用binary_crossentropy损失函数
  # e. 通常优化器选用rmsprop
  # f. 监控模型在训练集之外数据的性能，防止过拟合

主页

索引

模块索引

搜索页面