版权声明：所有的博客都是个人笔记，交流可以留言。未经允许，谢绝转载。。。 https://blog.csdn.net/qq_35976351/article/details/87738904
词向量和Embedding Layer简介
先给出学习的资料地址：
- https://www.youtube.com/watch?v=D-ekE-Wlcds
- https://towardsdatascience.com/deep-learning-4-embedding-layers-f9a02d55ac12
- https://towardsdatascience.com/machine-learning-text-processing-1d5a2d638958
- https://www.quora.com/What-is-word-embedding-in-deep-learning
- https://jjallaire.github.io/deep-learning-with-r-notebooks/notebooks/6.1-using-word-embeddings.nb.html
总结一句话：词向量给所有词典中的单词一个长度为N的特征向量，通过这个特征向量，来表示词的分布情况。不但节省空间，而且可以表示词之间的相似关系
卷积层简介
总结一句话：在尽量减少信息损失的情况下，降维处理，简化计算。
代码简介
导入数据
imdb = keras.datasets.imdb
(train_data, train_labels), (test_data, test_labels) = imdb.load_data(num_words=10000)
可以认为imdb是一个给单词编码的库，每个句子都把单词替换成了整型数据
把数字转换成单词
这里展示了一个一般的方法，词典的键值与值的转化方式：
word_index = imdb.get_word_index() # 单词是键值，数字是对应的编码
word_index = {k: (v + 3) for k, v in word_index.items()}
word_index["<PAD>"] = 0
word_index["<START>"] = 1
word_index["<UNK>"] = 2
word_index["<UNUSED>"] = 3
reverse_word_index = dict([(value, key) for (key, value) in word_index.items()])
def decode_word_review(text):
return ' '.join([reverse_word_index.get(i, '?') for i in text])
print(decode_word_review(train_data[0]))
这一步在训练中没用，只是个展示。。。
对句子长度进行标准化
训练集和测试集的句子长度不相同，需要统一长度，才能分批次进行训练：
train_data = keras.preprocessing.sequence.pad_sequences(train_data,
value=word_index["<PAD>"],
padding='post',
maxlen=256)
test_data = keras.preprocessing.sequence.pad_sequences(test_data,
value=word_index["<PAD>"],
padding='post',
maxlen=256)
print(len(train_data), len(train_data[1]))
配置模型
vocab_size = 10000
model = keras.Sequential()
model.add(keras.layers.Embedding(vocab_size, 16))
model.add(keras.layers.GlobalAveragePooling1D())
model.add(keras.layers.Dense(16, activation=tf.nn.relu))
model.add(keras.layers.Dense(1, activation=tf.nn.sigmoid))
Embedding层相当于处理词向量，之后进行一次卷积操作降维，其余的都是一般的层了。
model.compile(optimizer='adam',
loss='binary_crossentropy',
metrics=['accuracy'])
评估模型
扫描二维码关注公众号，回复：
5482543 查看本文章
result = model.evaluate(test_data, test_labels)
print(result)
history_dict = history.history
print(history_dict.keys())
完整版代码
from __future__ import absolute_import, division, print_function
import tensorflow as tf
from tensorflow import keras
print(tf.__version__)
imdb = keras.datasets.imdb
(train_data, train_labels), (test_data, test_labels) = imdb.load_data(num_words=10000)
print("Training e tries: {}, labels: {}".format(len(train_data), len(train_labels)))
print(train_data[0])
print(len(train_data[0]), len(train_data[1]))
word_index = imdb.get_word_index() # 单词是键值，数字是对应的编码
word_index = {k: (v + 3) for k, v in word_index.items()}
word_index["<PAD>"] = 0
word_index["<START>"] = 1
word_index["<UNK>"] = 2
word_index["<UNUSED>"] = 3
reverse_word_index = dict([(value, key) for (key, value) in word_index.items()])
def decode_word_review(text):
return ' '.join([reverse_word_index.get(i, '?') for i in text])
print(decode_word_review(train_data[0]))
train_data = keras.preprocessing.sequence.pad_sequences(train_data,
value=word_index["<PAD>"],
padding='post',
maxlen=256)
test_data = keras.preprocessing.sequence.pad_sequences(test_data,
value=word_index["<PAD>"],
padding='post',
maxlen=256)
print(len(train_data), len(train_data[1]))
# print(train_data[0])
vocab_size = 10000
model = keras.Sequential()
model.add(keras.layers.Embedding(vocab_size, 16))
model.add(keras.layers.GlobalAveragePooling1D())
model.add(keras.layers.Dense(16, activation=tf.nn.relu))
model.add(keras.layers.Dense(1, activation=tf.nn.sigmoid))
model.summary()
model.compile(optimizer='adam',
loss='binary_crossentropy',
metrics=['accuracy'])
x_val = train_data[:10000]
partial_x_train = train_data[10000:]
y_val = train_labels[:10000]
partial_y_train = train_labels[10000:]
history = model.fit(partial_x_train,
partial_y_train,
epochs=40,
batch_size=512,
validation_data=(x_val, y_val),
verbose=1)
result = model.evaluate(test_data, test_labels)
print(result)
history_dict = history.history
print(history_dict.keys())
import matplotlib.pyplot as plt
acc = history_dict['acc']
val_acc = history_dict['val_acc']
loss = history_dict['loss']
val_loss = history_dict['val_loss']
epochs = range(1, len(acc) + 1)
plt.subplot(2, 1, 1)
plt.plot(epochs, loss, 'bo', label='Training loss')
plt.plot(epochs, val_loss, 'b', label='Validation loss')
plt.title('Training and validation loss')
plt.xlabel('Epochs')
plt.ylabel('Loss')
plt.legend()
plt.subplot(2, 1, 2)
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()