使用 TensorFlow 的多标签文本分类 [英] Multilabel Text Classification using TensorFlow
问题描述
文本数据被组织为具有 20,000 个元素的向量,例如 [2, 1, 0, 0, 5, ...., 0].第 i 个元素表示第 i 个词在文本中的出现频率.
The text data is organized as vector with 20,000 elements, like [2, 1, 0, 0, 5, ...., 0]. i-th element indicates the frequency of the i-th word in a text.
ground truth 标签数据也表示为具有 4,000 个元素的向量,如 [0, 0, 1, 0, 1, ...., 0].第 i 个元素指示第 i 个标签是否是文本的正标签.文本的标签数量因文本而异.
The ground truth label data is also represented as vector with 4,000 elements, like [0, 0, 1, 0, 1, ...., 0]. i-th element indicates whether the i-th label is a positive label for a text. The number of labels for a text differs depending on texts.
我有一个用于单标签文本分类的代码.
I have a code for single-label text classification.
如何编辑以下用于多标签文本分类的代码?
How can I edit the following code for multilabel text classification?
特别是,我想知道以下几点.
Especially, I would like to know following points.
- 如何使用 TensorFlow 计算准确度.
- 如何设置一个阈值来判断标签是正还是负.例如,如果输出是 [0.80, 0.43, 0.21, 0.01, 0.32] 并且基本事实是 [1, 1, 0, 0, 1],那么分数超过 0.25 的标签应该被判断为正面.
谢谢.
import tensorflow as tf
# hidden Layer
class HiddenLayer(object):
def __init__(self, input, n_in, n_out):
self.input = input
w_h = tf.Variable(tf.random_normal([n_in, n_out],mean = 0.0,stddev = 0.05))
b_h = tf.Variable(tf.zeros([n_out]))
self.w = w_h
self.b = b_h
self.params = [self.w, self.b]
def output(self):
linarg = tf.matmul(self.input, self.w) + self.b
self.output = tf.nn.relu(linarg)
return self.output
# output Layer
class OutputLayer(object):
def __init__(self, input, n_in, n_out):
self.input = input
w_o = tf.Variable(tf.random_normal([n_in, n_out], mean = 0.0, stddev = 0.05))
b_o = tf.Variable(tf.zeros([n_out]))
self.w = w_o
self.b = b_o
self.params = [self.w, self.b]
def output(self):
linarg = tf.matmul(self.input, self.w) + self.b
self.output = tf.nn.relu(linarg)
return self.output
# model
def model():
h_layer = HiddenLayer(input = x, n_in = 20000, n_out = 1000)
o_layer = OutputLayer(input = h_layer.output(), n_in = 1000, n_out = 4000)
# loss function
out = o_layer.output()
cross_entropy = -tf.reduce_sum(y_*tf.log(out + 1e-9), name='xentropy')
# regularization
l2 = (tf.nn.l2_loss(h_layer.w) + tf.nn.l2_loss(o_layer.w))
lambda_2 = 0.01
# compute loss
loss = cross_entropy + lambda_2 * l2
# compute accuracy for single label classification task
correct_pred = tf.equal(tf.argmax(out, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, "float"))
return loss, accuracy
推荐答案
将relu改为sigmoid的输出层.将交叉熵损失修改为 sigmoid 交叉熵损失的显式数学公式(显式损失在我的案例/张量流版本中有效)
Change relu to sigmoid of output layer. Modify cross entropy loss to explicit mathematical formula of sigmoid cross entropy loss (explicit loss was working in my case/version of tensorflow )
import tensorflow as tf
# hidden Layer
class HiddenLayer(object):
def __init__(self, input, n_in, n_out):
self.input = input
w_h = tf.Variable(tf.random_normal([n_in, n_out],mean = 0.0,stddev = 0.05))
b_h = tf.Variable(tf.zeros([n_out]))
self.w = w_h
self.b = b_h
self.params = [self.w, self.b]
def output(self):
linarg = tf.matmul(self.input, self.w) + self.b
self.output = tf.nn.relu(linarg)
return self.output
# output Layer
class OutputLayer(object):
def __init__(self, input, n_in, n_out):
self.input = input
w_o = tf.Variable(tf.random_normal([n_in, n_out], mean = 0.0, stddev = 0.05))
b_o = tf.Variable(tf.zeros([n_out]))
self.w = w_o
self.b = b_o
self.params = [self.w, self.b]
def output(self):
linarg = tf.matmul(self.input, self.w) + self.b
#changed relu to sigmoid
self.output = tf.nn.sigmoid(linarg)
return self.output
# model
def model():
h_layer = HiddenLayer(input = x, n_in = 20000, n_out = 1000)
o_layer = OutputLayer(input = h_layer.output(), n_in = 1000, n_out = 4000)
# loss function
out = o_layer.output()
# modified cross entropy to explicit mathematical formula of sigmoid cross entropy loss
cross_entropy = -tf.reduce_sum( ( (y_*tf.log(out + 1e-9)) + ((1-y_) * tf.log(1 - out + 1e-9)) ) , name='xentropy' )
# regularization
l2 = (tf.nn.l2_loss(h_layer.w) + tf.nn.l2_loss(o_layer.w))
lambda_2 = 0.01
# compute loss
loss = cross_entropy + lambda_2 * l2
# compute accuracy for single label classification task
correct_pred = tf.equal(tf.argmax(out, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, "float"))
return loss, accuracy
这篇关于使用 TensorFlow 的多标签文本分类的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持IT屋!