主要内容:英文邮件分类、中文邮件分类【中英文邮件分类主要的区别在于embedding处,由于中文需要使用预训练词向量,而英文就不需要】
主要方法:TextCnn
一、英文邮件分类的代码实现
class TextCNN(object):
def __init__(self, text_length, nclasses, vocab_size,
embedding_size, filter_sizes, num_filters, l2_reg_lambda=0.0):
# feeds需要的参数
self.input_x = tf.placeholder(tf.int32, [None, text_length], name="input_x")
self.input_y = tf.placeholder(tf.float32, [None, nclasses], name="input_y")
self.dropout_keep_prob = tf.placeholder(tf.float32, name="dropout_keep_prob")
l2_loss = tf.constant(0.0) # 正则惩罚项的w
# embedding层
with tf.name_scope('embedding'):
self.W = tf.Variable(tf.random_uniform([vocab_size, embedding_size], -1.0, 1.0), name="W")
self.embedded_chars = tf.nn.embedding_lookup(self.W, self.input_x)
self.embedded_chars_expanded = tf.expand_dims(self.embedded_chars, -1)
# 卷积层和池化层
pool_outputs = []
for i, filter_size in enumerate(filter_sizes):
with tf.name_scope("conv-maxpool-%s" % filter_size):
# 卷积层
filter_shape = [filter_size, embedding_size, 1, num_filters]
W = tf.Variable(tf.truncated_normal(filter_shape, stddev=0.1), name="W")
b = tf.Variable(tf.constant(0.1, shape=[num_filters]), name="b")
conv = tf.nn.conv2d(
self.embedded_chars_expanded,
W,
strides=[1, 1, 1, 1],
padding="VALID",
name="conv")
h = tf.nn.relu(tf.nn.bias_add(conv, b), name="relu")
# 池化层
pooled = tf.nn.max_pool(
h,
ksize=[1, text_length - filter_size + 1, 1, 1],
strides=[1, 1, 1, 1],
padding="VALID",
name="pool")
pool_outputs.append(pooled)
# 全连接层
num_filters_total = num_filters * len(filter_sizes)
self.h_pool = tf.concat(pool_outputs, 0)
self.h_pool_flat = tf.reshape(self.h_pool, [-1, num_filters_total])
# dropout层
with tf.name_scope("dropout"):
self.h_drop = tf.nn.dropout(self.h_pool_flat, self.dropout_keep_prob)
# 输出层
with tf.name_scope("output"):
W = tf.get_variable(
"W",
shape=[num_filters_total, nclasses],
initializer=tf.contrib.layers.xavier_initializer()
)
b = tf.Variable(tf.constant(0.1, shape=[nclasses]), name="b")
l2_loss += tf.nn.l2_loss(W) # 正则惩罚项值的改变
l2_loss += tf.nn.l2_loss(b)
self.fin_out = tf.nn.xw_plus_b(self.h_drop, W, b, name="scores")
self.predictions = tf.argmax(self.fin_out, 1, name="predictions")
# 计算损失
with tf.name_scope("loss"):
losses = tf.nn.softmax_cross_entropy_with_logits(logits=self.fin_out, labels=self.input_y)
self.loss = tf.reduce_mean(losses) + l2_reg_lambda * l2_loss
# 计算准确度
with tf.name_scope("accuracy"):
correct_predictions = tf.equal(self.predictions, tf.argmax(self.input_y, 1))
self.accuracy = tf.reduce_mean(tf.cast(correct_predictions, "float"), name="accuracy")
二、中文邮件分类的代码实现
class TextCNN(object):
def __init__(self, text_length, nclasses, embedding_size, filter_sizes, num_filters, l2_reg_lambda=0.0):
# feeds需要的参数
self.input_x = tf.placeholder(tf.float32, [None, text_length, embedding_size], name="input_x")
self.input_y = tf.placeholder(tf.float32, [None, nclasses], name="input_y")
self.dropout_keep_prob = tf.placeholder(tf.float32, name="dropout_keep_prob")
l2_loss = tf.constant(0.0) # 正则惩罚项的w
# embedding层
with tf.name_scope('embedding'):
self.embedded_chars = self.input_x
self.embedded_chars_expanded = tf.expand_dims(self.embedded_chars, -1)
# 卷积层和池化层
pool_outputs = []
for i, filter_size in enumerate(filter_sizes):
with tf.name_scope("conv-maxpool-%s" % filter_size):
# 卷积层
filter_shape = [filter_size, embedding_size, 1, num_filters]
W = tf.Variable(tf.truncated_normal(filter_shape, stddev=0.1), name="W")
b = tf.Variable(tf.constant(0.1, shape=[num_filters]), name="b")
conv = tf.nn.conv2d(
self.embedded_chars_expanded,
W,
strides=[1, 1, 1, 1],
padding="VALID",
name="conv")
h = tf.nn.relu(tf.nn.bias_add(conv, b), name="relu")
# 池化层
pooled = tf.nn.max_pool(
h,
ksize=[1, text_length - filter_size + 1, 1, 1],
strides=[1, 1, 1, 1],
padding="VALID",
name="pool")
pool_outputs.append(pooled)
# 全连接层
num_filters_total = num_filters * len(filter_sizes)
self.h_pool = tf.concat(pool_outputs, 0) ,
self.h_pool_flat = tf.reshape(self.h_pool, [-1, num_filters_total])
# dropout层
with tf.name_scope("dropout"):
self.h_drop = tf.nn.dropout(self.h_pool_flat, self.dropout_keep_prob)
# 输出层
with tf.name_scope("output"):
W = tf.get_variable(
"W",
shape=[num_filters_total, nclasses],
initializer=tf.contrib.layers.xavier_initializer()
)
b = tf.Variable(tf.constant(0.1, shape=[nclasses]), name="b")
l2_loss += tf.nn.l2_loss(W) # 正则惩罚项值的改变
l2_loss += tf.nn.l2_loss(b)
self.fin_out = tf.nn.xw_plus_b(self.h_drop, W, b, name="scores")
self.predictions = tf.argmax(self.fin_out, 1, name="predictions")
# 计算损失
with tf.name_scope("loss"):
losses = tf.nn.softmax_cross_entropy_with_logits(logits=self.fin_out, labels=self.input_y)
self.loss = tf.reduce_mean(losses) + l2_reg_lambda * l2_loss
# 计算准确度
with tf.name_scope("accuracy"):
correct_predictions = tf.equal(self.predictions, tf.argmax(self.input_y, 1))
self.accuracy = tf.reduce_mean(tf.cast(correct_predictions, "float"), name="accuracy")