循环神经网络--Keras 例程lmdb_lstm.py理解

1、官网下载后，直接运行lmdb_lstm.py。但是下载的速度很慢。

解决办法： 在Ubuntu16.04系统下，首先下载imdb.npz数据集（百度网盘下载地址），只需将 imdb.npz放在 ~/.keras/datasets/ 目录下即可。

在命令窗口进入imdb.npz数据集当前下载目录，然后输入：

sudo mkdir ~/.keras/datasets/
sudo cp imdb.npz ~/.keras/datasets/

运行例程，即可跳过下载数据过程。

2、程序分析

# -*- coding: utf-8 -*-

# 加载 Keras 模型相关的 Python 模块
import numpy as np
np.random.seed(1337)  # for reproducibility

from keras.preprocessing import sequence
from keras.models import Sequential
from keras.layers import Dense, Activation, Embedding
from keras.layers import LSTM
from keras.datasets import imdb

max_features = 20000
maxlen = 80  # cut texts after this number of words (among top max_features most common words)
batch_size = 32

# 加载数据
print('Loading data...')
(X_train, y_train), (X_test, y_test) = imdb.load_data(nb_words=max_features)
print(len(X_train), 'train sequences')
print(len(X_test), 'test sequences')

# 数据预处理
print('Pad sequences (samples x time)')
X_train = sequence.pad_sequences(X_train, maxlen=maxlen)
X_test = sequence.pad_sequences(X_test, maxlen=maxlen)
print('X_train shape:', X_train.shape)
print('X_test shape:', X_test.shape)

# 构建 LSTM 模型
print('Build model...')
model = Sequential()
model.add(Embedding(max_features, 128, dropout=0.2)) # 词嵌入
model.add(LSTM(128, dropout_W=0.2, dropout_U=0.2)) # LSTM 层
model.add(Dense(1))# 二分类层
model.add(Activation('sigmoid'))
model.summary() # 打印模型

# try using different optimizers and different optimizer configs
model.compile(loss='binary_crossentropy',
              optimizer='adam',
              metrics=['accuracy'])

print('Train...')
model.fit(X_train, y_train, batch_size=batch_size, nb_epoch=15,
          validation_data=(X_test, y_test))
score, acc = model.evaluate(X_test, y_test,
                            batch_size=batch_size)
print('Test score:', score)
print('Test accuracy:', acc)

参考文献：

1. 利用 TensorFlow 高级 API Keras 实现 MLP，CNN，LSTM
2. Keras Recurrent Layers 解析
3. IMDB Movie reviews sentiment classification
4. IMDB影评倾向分类
5. IMDB影评倾向分类 - N-Gram