textcnn自己的理解

最新推荐文章于 2024-09-12 10:37:07 发布

沐自礼

最新推荐文章于 2024-09-12 10:37:07 发布

阅读量2.5k

点赞数 1

分类专栏： nlp算法 TensorFlow，rnn 文章标签： nlp

本文链接：https://blog.csdn.net/nanjifengzi/article/details/77196726

版权

nlp算法同时被 2 个专栏收录

10 篇文章 1 订阅

订阅专栏

TensorFlow，rnn

7 篇文章 0 订阅

订阅专栏

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.
    """
        # sequence_length-最长词汇数
    # num_classes-分类数
    # vocab_size-总词汇数
    # embedding_size-词向量长度
    # filter_sizes-卷积核尺寸3，4，5
    # num_filters-卷积核数量
    # l2_reg_lambda-l2正则化系数
    def __init__(
      self, sequence_length, num_classes, vocab_size,
      embedding_size, filter_sizes, num_filters, l2_reg_lambda=0.0):

        # 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"):
            self.W = tf.Variable(
                    #19758   128
                tf.random_uniform([vocab_size, embedding_size], -1.0, 1.0),
                name="W")
            #input_x  %len(w)  
            self.embedded_chars = tf.nn.embedding_lookup(self.W, self.input_x)
            #add one vector
            # 添加一个维度，[batch_size, sequence_length, embedding_size, 1]
            self.embedded_chars_expanded = tf.expand_dims(self.embedded_chars, -1)

        # Create a convolution + maxpool layer for each filter size
        pooled_outputs = []
        #3 4 5
        for i, filter_size in enumerate(filter_sizes):
            with tf.name_scope("conv-maxpool-%s" % filter_size):
                # Convolution Layer   3,128,1,2
                filter_shape = [filter_size, embedding_size, 1, num_filters]
                #随机生成正太分布
                W = tf.Variable(tf.truncated_normal(filter_shape, stddev=0.1), name="W")
                #
                #   2
                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
                # 56 -(3,4,5) + 1
                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
        
        #将pooled_outputs中的值全部取出来然后reshape成[len(input_x),num_filters*len(filters_size)]，然后进行了dropout层防止过拟合，
        #最后再添加了一层全连接层与softmax层将特征映射成不同类别上的概率
        #2 3   把池化层输出变成一维向量
        num_filters_total = num_filters * len(filter_sizes)
        self.h_pool = tf.concat(pooled_outputs, 3)
        #    , 6
        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"):
            #6,2
            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 way
            l2_loss += tf.nn.l2_loss(W)
            l2_loss += tf.nn.l2_loss(b)
            #computes matmul(x, weights) + biases.

            self.scores = tf.nn.xw_plus_b(self.h_drop, W, b, name="scores")
            self.predictions = tf.argmax(self.scores, 1, name="predictions")

        # CalculateMean cross-entropy loss
        with tf.name_scope("loss"):
            #Computes softmax cross entropy between `logits` and `labels`.

            losses = tf.nn.softmax_cross_entropy_with_logits(logits=self.scores, labels=self.input_y)
            #计算张量的尺寸的元素平均值。
            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")