一張圖幫你弄懂text-cnn

1、何為textcnn

利用卷積神經網路對文字進行分類的演算法,那如何用卷積神經網路對文字進行分類呢。這裡就tensorflow版本的textcnn原始碼分析一波。要知道,對文字向量化之後一般是一個一維向量來代表這個文字,但是卷積神經網路一般是對影象進行處理的,那如何將一維轉化成二維呢,textcnn在卷積層之前設定了一個embedding層,即將詞向量嵌入進去。那具體如何操作的呢。

比如一句話(“白條”,“如何”,“開通”),假設給每個詞一個id{“白條”:1,“如何”:2,“開通”:3},文字向量化之後則是【1,2,3】的一個一維向量,但是無法滿足卷積層的輸入,所以嵌入一個embedding層,此時假設每個詞都有一個3維的詞向量,{“白條”:【2,3,4】,“如何”:【3,5,1】,“開通”:【4,5,6】},則通過embedding層的對映,原文字經過詞向量嵌入之後變成【【2,3,4】,【3,5,1】,【4,5,6】】的二維向量,當然卷積神經網路對影象進行卷積時還有通道一說,這裡對二維向量可以自動擴充一個維度以滿足通道的這一個維度。

2、textcnn tensorflow 結構程式碼

'''
__author__ : 'shizhengxin'
'''
import tensorflow as tf
import numpy as np
class TextCNN(object):
"""
A CNN for text classification.
Uses an embedding layer, followed by a convolutional, max-pooling and softmax layer.
"""
def __init__(
self, sequence_length, num_classes, vocab_size  ,embedding_matrix,
embedding_size, filter_sizes, num_filters, l2_reg_lambda=0.0):
# embedding_matrix,
# Placeholders for input, output and dropout
self.input_x = tf.placeholder(tf.int32, [None, sequence_length], name="input_x")
self.input_y = tf.placeholder(tf.float32, [None, num_classes], name="input_y")
self.dropout_keep_prob = tf.placeholder(tf.float32, name="dropout_keep_prob")
# Keeping track of l2 regularization loss (optional)
l2_loss = tf.constant(0.0)
#Embedding layer
# with tf.device('/cpu:0'), tf.name_scope("embedding"):
#     W = tf.Variable(
#         tf.random_uniform([vocab_size, embedding_size], -1.0, 1.0),
#         name="W")
#     self.embedded_chars = tf.nn.embedding_lookup(W, self.input_x)
#     self.embedded_chars_expanded = tf.expand_dims(self.embedded_chars, -1)
with tf.device('/cpu:0'), tf.name_scope("embedding"):
self.embedded_chars = tf.nn.embedding_lookup(embedding_matrix, self.input_x)
self.embedded_chars_expanded = tf.expand_dims(self.embedded_chars, -1)
self.embedded_chars_expanded = tf.cast(self.embedded_chars_expanded,dtype=tf.float32)
print(self.embedded_chars_expanded.shape)
# Create a convo
#
# lution   maxpool layer for each filter size
pooled_outputs = []
for i, filter_size in enumerate(filter_sizes):
with tf.name_scope("conv-maxpool-%s" % filter_size):
# Convolution Layer
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")
# Apply nonlinearity
h = tf.nn.relu(tf.nn.bias_add(conv, b), name="relu")
# Maxpooling over the outputs
pooled = tf.nn.max_pool(
h,
ksize=[1, sequence_length - filter_size   1, 1, 1],
strides=[1, 1, 1, 1],
padding='VALID',
name="pool")
pooled_outputs.append(pooled)
# Combine all the pooled features
num_filters_total = num_filters * len(filter_sizes)
self.h_pool = tf.concat(pooled_outputs, 3)
self.h_pool_flat = tf.reshape(self.h_pool, [-1, num_filters_total])
# Add dropout
with tf.name_scope("dropout"):
self.h_drop = tf.nn.dropout(self.h_pool_flat, self.dropout_keep_prob)
# Final (unnormalized) scores and predictions
with tf.name_scope("output"):
W = tf.get_variable(
"W",
shape=[num_filters_total, num_classes],
initializer=tf.contrib.layers.xavier_initializer())
b = tf.Variable(tf.constant(0.1, shape=[num_classes]), name="b")
l2_loss  = tf.nn.l2_loss(W)
l2_loss  = tf.nn.l2_loss(b)
self.scores = tf.nn.xw_plus_b(self.h_drop, W, b, name="scores")
self.probability = tf.nn.sigmoid(self.scores)
self.predictions = tf.argmax(self.scores, 1, name="predictions")
# CalculateMean cross-entropy loss
with tf.name_scope("loss"):
losses = tf.nn.softmax_cross_entropy_with_logits(labels=self.input_y, logits=self.scores)
self.loss = tf.reduce_mean(losses)   l2_reg_lambda * l2_loss
# Accuracy
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")

可以看出textcnn的卷積方式是對輸入層做三次不同卷積核的卷積,每次卷積後進行池化。

3、一張圖讓你搞懂textcnn

這是我畫的一張textcnn結構圖

1、首先輸入層,將文字經過embedding之後形成了一個2000*300的維度,其中2000為文字最大長度、300為詞向量的維度。

2、卷積層,卷積層設計三個不同大小的卷積核,【3*300,4*300,5*300】,每個不同大小的卷積核各128個。卷積後分別成為【1998*1*128,1997*1*128,1996*1*128】的feture-map,這裡為什麼會變成大小這樣的,是因為tensorflow的卷積方式採用same 或者 valid的形式,這種卷積的方式採用的是valid 具體大家可以看看官方文件。

3、經過卷積之後,隨後是三個池化層,池化層的目的是縮小特徵圖,這裡同池化層的設定,將卷積層的特徵池化之後的圖為【1*1*128,1*1*128,1*1*28】,經過reshape維度合併成【3*128】。

4、全連線層就不必說,採用softmax就可以解決了。