一维卷积filter_TensorFlow实现卷积神经网络之邮件分类

背景知识

TensorFlow 也可以应用于文本的处理。 本节将利用TensorFlow框架实现卷积神经网络邮件分类。

1， 怎样给文字编码？

这是我们遇到的第一个问题，它不像图像那样H*W*C 在经过一定的reshape就可以了，文字的编码比较复杂一点。需要经过一个embedding layer，结合本例，大体的过程如下几步？

• 1， 文字分词，规范化
• 2， 计算最长文本个数，对其文本使用 learn.preprocessing.VocabularyProcessor，对文本进行预处理
• 3， 对文本进行向量化，并经过 embedding layer 将稀疏矩阵进行稠密化处理。

2，Embedding layer 干啥的？

One-hot 简单直接，通俗易懂，但是他的缺点是：

• 1、会产生大量冗余的稀疏矩阵
• 2、维度（单词）间的关系，没有得到体现

接下来就是要对稀疏矩阵进行压缩，简单的说这就是embedding 干的事情。举个例子有，girl, woman, boy, man 四个词，可以用两个节点去表示四个单词。每个节点取不同值时的意义如下表

这时候 gill 就可以用 [0,1] 表示。 这样就把一维的稀矩阵转化为一个二维的矩阵。大体的思想就是这样的，当然了有兴趣的可以看下word2vect 的表示方法。

Note：最大的特殊之处就是： 在卷积层需要有不同大小的 filter去和输入的数据卷积，不同的filter卷积的结果还要被拼合在一起，进行下一步特征的抽取。

具体的流程可以用下图表示：

Fig.1, 文本处理流程框架图。

利用VocabularyProcessor函数，将文字用one-hot 的形式进行处理，设计三种不同的filter [3,4,5] 每种的滤波器有128个。Filter和输入的数据进行卷积后得到的特种矩阵，在进行拼合处理，最后将拼合的矩阵进行拉平，通过卷积模型进行结果的输出。

一，导入所需要的库

将获取训练数据的函数放在 data_helpers中，模型的训练函数在text_cnn 中的TextCNN 中，把相应的文件放在与主程序同一个目录中，导入所需要的函数。

import tensorflow as tf
import numpy as np
import os
import time
import datetime
import data_helpers
from text_cnn import TextCNN
from tensorflow.contrib import learn

二，参数初始化

采用 tf.flages.DEFINE 的形式定义初始化参数。tf.app.flags.DEFINE_xxx() 就是添加命令行的optional argument（可选参数），而 tf.app.flags.FLAGS 可以从对应的命令行参数取出参数。

需要注意的是，当运行第一次的时候没有报错，但是在此运行的时候就会出现错误，此时解决的办法就是再打开一个console 运行就可以了。

# Data loading params
tf.flags.DEFINE_float("dev_sample_percentage", .4, "Percentage of the training data to use for validation")
tf.flags.DEFINE_string("positive_data_file", "./data/rt-polaritydata/rt-polarity.pos", "Data source for the positive data")
tf.flags.DEFINE_string("negative_data_file", "./data/rt-polaritydata/rt-polarity.neg", "Data source for the negative data")

# Model Hyperparameters
tf.flags.DEFINE_integer("embedding_dim", 128, "Dimensionality of character embedding (default: 128)")
tf.flags.DEFINE_string("filter_sizes", "3,4,5", "Comma-separated filter sizes (default: '3,4,5')")
tf.flags.DEFINE_integer("num_filters", 128, "Number of filters per filter size (default: 128)")
tf.flags.DEFINE_float("dropout_keep_prob", 0.5, "Dropout keep probability (default: 0.5)")
tf.flags.DEFINE_float("l2_reg_lambda", 0.0, "L2 regularization lambda (default: 0.0)")

# Training parameters
tf.flags.DEFINE_integer("batch_size", 64, "Batch Size (default: 64)")
tf.flags.DEFINE_integer("num_epochs", 200, "Number of training epochs (default: 200)")
tf.flags.DEFINE_integer("evaluate_every", 100, "Evaluate model on dev set after this many steps (default: 100)")
tf.flags.DEFINE_integer("checkpoint_every", 100, "Save model after this many steps (default: 100)")
tf.flags.DEFINE_integer("num_checkpoints", 5, "Number of checkpoints to store (default: 5)")
# Misc Parameters
tf.flags.DEFINE_boolean("allow_soft_placement", True, "Allow device soft device placement")
tf.flags.DEFINE_boolean("log_device_placement", False, "Log placement of ops on devices")

FLAGS = tf.flags.FLAGS
FLAGS._parse_flags()

#print("nParameters:")
#for attr, value in sorted(FLAGS.__flags.items()):
#    print("{}={}".format(attr.upper(), value))
#print("")

3，数据预处理

x_text, y = data_helpers.load_data_and_labels(FLAGS.positive_data_file, FLAGS.negative_data_file)

# Build vocabulary
# 保证所有邮件长度的大小是一致的
max_document_length = max([len(x.split(" ")) for x in x_text])
vocab_processor = learn.preprocessing.VocabularyProcessor(max_document_length)
x = np.array(list(vocab_processor.fit_transform(x_text)))

# Randomly shuffle data
np.random.seed(10)
shuffle_indices = np.random.permutation(np.arange(len(y)))
x_shuffled = x[shuffle_indices]
y_shuffled = y[shuffle_indices]

# Split train/test set
# TODO: This is very crude, should use cross-validation
dev_sample_index = -1 * int(FLAGS.dev_sample_percentage * float(len(y))) # -1 是指从后向前取值
x_train, x_dev = x_shuffled[:dev_sample_index], x_shuffled[dev_sample_index:]
y_train, y_dev = y_shuffled[:dev_sample_index], y_shuffled[dev_sample_index:]
print("Vocabulary Size: {:d}".format(len(vocab_processor.vocabulary_)))
print("Train/Dev split: {:d}/{:d}".format(len(y_train), len(y_dev)))

4, 模型训练

with tf.Graph().as_default():
    # session device和log 参数设置
    session_conf = tf.ConfigProto(
      allow_soft_placement=FLAGS.allow_soft_placement,
      log_device_placement=FLAGS.log_device_placement)
    sess = tf.Session(config=session_conf)
    # thestructure ofCNN
    with sess.as_default():
        cnn = TextCNN(
                      
            sequence_length=x_train.shape[1], 
            num_classes=y_train.shape[1],
            vocab_size=len(vocab_processor.vocabulary_),
            embedding_size=FLAGS.embedding_dim,
            filter_sizes=list(map(int, FLAGS.filter_sizes.split(","))), # 字符串转化为字典
            num_filters=FLAGS.num_filters,
            l2_reg_lambda=FLAGS.l2_reg_lambda
            
            )

        # Define Training procedure
        global_step = tf.Variable(0, name="global_step", trainable=False)
        optimizer = tf.train.AdamOptimizer(1e-3)
        grads_and_vars = optimizer.compute_gradients(cnn.loss)
        train_op = optimizer.apply_gradients(grads_and_vars, global_step=global_step)

        # Keep track of gradient values and sparsity (optional)
        
#        grad_summaries = []
#        for g, v in grads_and_vars:
#            if g is not None:
#                grad_hist_summary = tf.summary.histogram("{}/grad/hist".format(v.name), g)
#                sparsity_summary = tf.summary.scalar("{}/grad/sparsity".format(v.name), tf.nn.zero_fraction(g))
#                grad_summaries.append(grad_hist_summary)
#                grad_summaries.append(sparsity_summary)
#        grad_summaries_merged = tf.summary.merge(grad_summaries)

        # Output directory for models and summaries
        timestamp = str(int(time.time()))
        out_dir = os.path.abspath(os.path.join(os.path.curdir, "runs", timestamp))
        print("Writing to {}n".format(out_dir))

        # Summaries for loss and accuracy
        loss_summary = tf.summary.scalar("loss", cnn.loss)
        acc_summary = tf.summary.scalar("accuracy", cnn.accuracy)

        # Train Summaries
#        train_summary_op = tf.summary.merge([loss_summary, acc_summary, grad_summaries_merged])
#        train_summary_dir = os.path.join(out_dir, "summaries", "train")
#        train_summary_writer = tf.summary.FileWriter(train_summary_dir, sess.graph)

        # Dev summaries
        dev_summary_op = tf.summary.merge([loss_summary, acc_summary])
        dev_summary_dir = os.path.join(out_dir, "summaries", "dev")
        dev_summary_writer = tf.summary.FileWriter(dev_summary_dir, sess.graph)

        # Checkpoint directory. Tensorflow assumes this directory already exists so we need to create it
        checkpoint_dir = os.path.abspath(os.path.join(out_dir, "checkpoints"))
        checkpoint_prefix = os.path.join(checkpoint_dir, "model")
        if not os.path.exists(checkpoint_dir):
            os.makedirs(checkpoint_dir)
        saver = tf.train.Saver(tf.global_variables(), max_to_keep=FLAGS.num_checkpoints)

        # Write vocabulary
        vocab_processor.save(os.path.join(out_dir, "vocab"))

        # Initialize all variables
        sess.run(tf.global_variables_initializer())

        def train_step(x_batch, y_batch):
            """
            A single training step
            """
            feed_dict = {
              cnn.input_x: x_batch,
              cnn.input_y: y_batch,
              cnn.dropout_keep_prob: FLAGS.dropout_keep_prob
            }
#            _, step, summaries, loss, accuracy = sess.run(
#                [train_op, global_step, train_summary_op, cnn.loss, cnn.accuracy],
#                feed_dict)
            _, step, loss, accuracy = sess.run(
                [train_op, global_step, cnn.loss, cnn.accuracy],
                feed_dict)
            time_str = datetime.datetime.now().isoformat()
            print("{}: step {}, loss {:g}, acc {:g}".format(time_str, step, loss, accuracy))
#            train_summary_writer.add_summary(summaries, step)

        def dev_step(x_batch, y_batch, writer=None):
            """
            Evaluates model on a dev set
            """
            feed_dict = {
              cnn.input_x: x_batch,
              cnn.input_y: y_batch,
              cnn.dropout_keep_prob: 1.0
            }
            step, summaries, loss, accuracy = sess.run(
                [global_step, dev_summary_op, cnn.loss, cnn.accuracy],
                feed_dict)
            time_str = datetime.datetime.now().isoformat()
            print("{}: step {}, loss {:g}, acc {:g}".format(time_str, step, loss, accuracy))
            if writer:
                writer.add_summary(summaries, step)

        # Generate batches
        batches = data_helpers.batch_iter(
            list(zip(x_train, y_train)), FLAGS.batch_size, FLAGS.num_epochs)
        # Training loop. For each batch...
        for batch in batches:
            x_batch, y_batch = zip(*batch)
            train_step(x_batch, y_batch)
            current_step = tf.train.global_step(sess, global_step)
            if current_step % FLAGS.evaluate_every == 0:
                print("nEvaluation:")
                dev_step(x_dev, y_dev, writer=dev_summary_writer)
                print("")
            if current_step % FLAGS.checkpoint_every == 0:
                path = saver.save(sess, './', global_step=current_step)
                print("Saved model checkpoint to {}n".format(path))

函数参数解释：

tf.nn.embedding_lookup函数的用法主要是选取一个张量里面索引对应的元素。tf.nn.embedding_lookup（tensor, id）:tensor就是输入张量，id就是张量对应的索引，其他的参数不介绍。

https://blog.csdn.net/u010412858/article/details/77848878

代码下载地址