2018年10月4日笔记
tensorflow是谷歌google的深度学习框架,tensor中文叫做张量,flow叫做流。 CNN是convolutional neural network的简称,中文叫做卷积神经网络。 文本分类是NLP(自然语言处理)的经典任务。
操作系统:Win10 tensorflow版本:1.6 tensorboard版本:1.6 python版本:3.6
本文是作者学习《使用卷积神经网络以及循环神经网络进行中文文本分类》的成果,感激前辈; github链接:https://github.com/gaussic/text-classification-cnn-rnn
使用循环神经网络模型要求有较高的机器配置,如果使用CPU版tensorflow会花费大量时间。 读者在有nvidia显卡的情况下,安装GPU版tensorflow会提高计算速度50倍。 安装教程链接:https://blog.csdn.net/qq_36556893/article/details/79433298 如果没有nvidia显卡,但有visa信用卡,请阅读我的另一篇文章《在谷歌云服务器上搭建深度学习平台》,链接:https://www.jianshu.com/p/893d622d1b5a
数据集下载链接: https://pan.baidu.com/s/1oLZZF4AHT5X_bzNl2aF2aQ 提取码: 5sea 下载压缩文件cnews.zip完成后,选择解压到cnews。 文件夹结构如下图所示:
image.png
代码文件需要放到和cnews文件夹同级目录。
with open('./cnews/cnews.train.txt', encoding='utf8') as file:
line_list = [k.strip() for k in file.readlines()]
train_label_list = [k.split()[0] for k in line_list]
train_content_list = [k.split(maxsplit=1)[1] for k in line_list]
with open('./cnews/cnews.vocab.txt', encoding='utf8') as file:
vocabulary_list = [k.strip() for k in file.readlines()]
word2id_dict = dict(((b, a) for a, b in enumerate(vocabulary_list)))
content2vector = lambda content : [word2id_dict[word] for word in content if word in word2id_dict]
train_vector_list = [content2vector(content) for content in train_content_list ]
vocab_size = 5000 # 词汇表达小
embedding_dim = 64 # 词向量维度
seq_length = 600 # 序列长度
num_classes = 10 # 类别数
num_filters = 256 # 卷积核数目
kernel_size = 5 # 卷积核尺寸
hidden_dim = 128 # 全连接层神经元
dropout_keep_prob = 0.5 # dropout保留比例
learning_rate = 1e-3 # 学习率
batch_size = 64 # 每批训练大小
import tensorflow.contrib.keras as kr
train_X = kr.preprocessing.sequence.pad_sequences(train_vector_list, 600)
from sklearn.preprocessing import LabelEncoder
labelEncoder = LabelEncoder()
train_y = labelEncoder.fit_transform(train_label_list)
train_Y = kr.utils.to_categorical(train_y, num_classes=10)
import tensorflow as tf
tf.reset_default_graph()
X_holder = tf.placeholder(tf.int32, [None, seq_length])
Y_holder = tf.placeholder(tf.float32, [None, num_classes])
embedding = tf.get_variable('embedding', [vocab_size, embedding_dim])
embedding_inputs = tf.nn.embedding_lookup(embedding, X_holder)
conv = tf.layers.conv1d(embedding_inputs, num_filters, kernel_size)
max_pooling = tf.reduce_max(conv, reduction_indices=[1])
full_connect = tf.layers.dense(max_pooling, hidden_dim)
full_connect_dropout = tf.contrib.layers.dropout(full_connect, keep_prob=1)
full_connect_activate = tf.nn.relu(full_connect_dropout)
softmax_before = tf.layers.dense(full_connect_activate, num_classes)
predict_Y = tf.nn.softmax(softmax_before)
cross_entropy = tf.nn.softmax_cross_entropy_with_logits_v2(labels=Y_holder, logits=softmax_before)
loss = tf.reduce_mean(cross_entropy)
optimizer = tf.train.AdamOptimizer(learning_rate)
train = optimizer.minimize(loss)
isCorrect = tf.equal(tf.argmax(Y_holder, 1), tf.argmax(predict_Y, 1))
accuracy = tf.reduce_mean(tf.cast(isCorrect, tf.float32))
init = tf.global_variables_initializer()
session = tf.Session()
session.run(init)
import random
for i in range(3000):
selected_index = random.sample(list(range(len(train_y))), k=64)
batch_X = train_X[selected_index]
batch_Y = train_Y[selected_index]
session.run(train, {X_holder:batch_X, Y_holder:batch_Y})
step = i + 1
if step % 100 == 0:
selected_index = random.sample(list(range(len(train_y))), k=200)
batch_X = train_X[selected_index]
batch_Y = train_Y[selected_index]
loss_value, accuracy_value = session.run([loss, accuracy], {X_holder:batch_X, Y_holder:batch_Y})
print('step:%d loss:%.4f accuracy:%.4f' %(step, loss_value, accuracy_value))
上面一段代码的运行结果如下(只截取前十行):
step:100 loss:0.5491 accuracy:0.8650 step:200 loss:0.2495 accuracy:0.9200 step:300 loss:0.1928 accuracy:0.9450 step:400 loss:0.1123 accuracy:0.9700 step:500 loss:0.1183 accuracy:0.9800 step:600 loss:0.0946 accuracy:0.9800 step:700 loss:0.1316 accuracy:0.9600 step:800 loss:0.1455 accuracy:0.9650 step:900 loss:0.1226 accuracy:0.9600 step:1000 loss:0.0686 accuracy:0.9800
with open('./cnews/cnews.train.txt', encoding='utf8') as file:
line_list = [k.strip() for k in file.readlines()]
train_label_list = [k.split()[0] for k in line_list]
train_content_list = [k.split(maxsplit=1)[1] for k in line_list]
with open('./cnews/cnews.vocab.txt', encoding='utf8') as file:
vocabulary_list = [k.strip() for k in file.readlines()]
word2id_dict = dict(((b, a) for a, b in enumerate(vocabulary_list)))
content2vector = lambda content : [word2id_dict[word] for word in content if word in word2id_dict]
train_vector_list = [content2vector(content) for content in train_content_list ]
vocab_size = 5000 # 词汇表达小
embedding_dim = 64 # 词向量维度
seq_length = 600 # 序列长度
num_classes = 10 # 类别数
num_filters = 256 # 卷积核数目
kernel_size = 5 # 卷积核尺寸
hidden_dim = 128 # 全连接层神经元
dropout_keep_prob = 0.5 # dropout保留比例
learning_rate = 1e-3 # 学习率
batch_size = 64 # 每批训练大小
import tensorflow.contrib.keras as kr
train_X = kr.preprocessing.sequence.pad_sequences(train_vector_list, 600)
from sklearn.preprocessing import LabelEncoder
labelEncoder = LabelEncoder()
train_y = labelEncoder.fit_transform(train_label_list)
train_Y = kr.utils.to_categorical(train_y, num_classes=10)
import tensorflow as tf
tf.reset_default_graph()
X_holder = tf.placeholder(tf.int32, [None, seq_length])
Y_holder = tf.placeholder(tf.float32, [None, num_classes])
embedding = tf.get_variable('embedding', [vocab_size, embedding_dim])
embedding_inputs = tf.nn.embedding_lookup(embedding, X_holder)
conv = tf.layers.conv1d(embedding_inputs, num_filters, kernel_size)
max_pooling = tf.reduce_max(conv, reduction_indices=[1])
full_connect = tf.layers.dense(max_pooling, hidden_dim)
full_connect_dropout = tf.contrib.layers.dropout(full_connect, keep_prob=1)
full_connect_activate = tf.nn.relu(full_connect_dropout)
softmax_before = tf.layers.dense(full_connect_activate, num_classes)
predict_Y = tf.nn.softmax(softmax_before)
cross_entropy = tf.nn.softmax_cross_entropy_with_logits_v2(labels=Y_holder, logits=softmax_before)
loss = tf.reduce_mean(cross_entropy)
optimizer = tf.train.AdamOptimizer(learning_rate)
train = optimizer.minimize(loss)
isCorrect = tf.equal(tf.argmax(Y_holder, 1), tf.argmax(predict_Y, 1))
accuracy = tf.reduce_mean(tf.cast(isCorrect, tf.float32))
init = tf.global_variables_initializer()
session = tf.Session()
session.run(init)
import random
for i in range(3000):
selected_index = random.sample(list(range(len(train_y))), k=64)
batch_X = train_X[selected_index]
batch_Y = train_Y[selected_index]
session.run(train, {X_holder:batch_X, Y_holder:batch_Y})
step = i + 1
if step % 100 == 0:
selected_index = random.sample(list(range(len(train_y))), k=200)
batch_X = train_X[selected_index]
batch_Y = train_Y[selected_index]
loss_value, accuracy_value = session.run([loss, accuracy], {X_holder:batch_X, Y_holder:batch_Y})
print('step:%d loss:%.4f accuracy:%.4f' %(step, loss_value, accuracy_value))