tensorflow使用CNN中实现文本分类

- 本文翻译自WILDML的博客Implementing a CNN for Text Classification in TensorFlow 
- 博客地址： http://www.wildml.com/2015/12/implementing-a-cnn-for-text-classification-in-tensorflow/ 
- github地址：https://github.com/dennybritz/cnn-text-classification-tf

在这篇文章中，我们将实现一个类似于Kim Yoon的卷积神经网络语句分类模型。 本文提出的模型在一系列文本分类任务（如情绪分析）中实现了良好的分类性能，并已成为新的文本分类架构的标准基准。

我假设你已经熟悉了应用于NLP的卷积神经网络的基础知识。 如果没有，我建议先阅读NLP的理解卷积神经网络，以获得必要的背景。

我们将在这篇文章中建立的网络大致如下： 

第一层将单词嵌入到低维向量中。 下一层使用多个过滤器大小对嵌入的字矢量进行卷积。 例如，一次滑过3个，4个或5个字。 接下来，我们将卷积层的结果最大化为一个长的特征向量，添加退出正则化，并使用softmax层对结果进行分类。

因为这是一个教育文章，我决定从原始文件中简化模型： 
- 我们不会将预先训练的word2vec矢量用于我们的词嵌入。 相反，我们从头开始学习嵌入。 
- 我们不会对权重向量执行L2规范约束。 （和从业者指南）对句子分类的卷积神经网络的敏感性分析发现，约束对最终结果几乎没有影响。 
- 原始实验用两个输入数据通道 - 静态和非静态字矢量。 我们只使用一个通道。

定义网络层

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_size, filter_sizes, num_filters,
            l2_reg_lambda=0.0):
        '''
        :param sequence_length:The length of our sentences. Remember that we padded all our sentences to have the same length (59 for our data set).
        :param num_classes:Number of classes in the output layer, two in our case (positive and negative).
        :param vocab_size:The size of our vocabulary. This is needed to define the size of our embedding layer, which will have shape [vocabulary_size, embedding_size].
        :param embedding_size: The dimensionality of our embeddings.
        :param filter_sizes:The number of words we want our convolutional filters to cover. We will have num_filters for each size specified here.
        For example, [3, 4, 5] means that we will have filters that slide over 3, 4 and 5 words respectively, for a total of 3 * num_filters filters.
        :param num_filters:The number of filters per filter size (see above).
        :param l2_reg_lambda:l2_reg_lambda
        '''

        # 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
        # W是我们在训练中学习的嵌入矩阵。 我们使用随机均匀分布来初始化它。 tf.nn.embedding_lookup创建实际的嵌入操作。
        # 嵌入操作的结果是形状为[None，sequence_length，embedding_size]的三维张量。
        # TensorFlow的卷积conv2d操作期望具有对应于批次，宽度，高度和通道的尺寸的四维张量。
        # 我们嵌入的结果不包含通道尺寸，所以我们手动添加它们，留下一层形状[None，sequence_length，embedding_size，1]。
        with tf.device('/cpu:0'), tf.name_scope('embedding'):
            self.W = tf.Variable(tf.random_uniform([vocab_size, embedding_size], -1.0, 1.0))
            self.embedded_chars = tf.nn.embedding_lookup(self.W, self.input_x)
            self.embedded_chars_expanded = tf.expand_dims(self.embedded_chars, -1)

        # Create a convolution + maxpool layer for each filter size
        # 我们使用不同大小的过滤器。 因为每个卷积产生不同形状的张量，我们需要迭代它们，为它们中的每一个创建一个层，然后将结果合并成一个大的特征向量。
        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')
                # “VALID”填充意味着我们将过滤器滑过我们的句子而不填充边缘，执行一个窄的卷积，给出一个形状[1，sequence_length - filter_size + 1,1,1]的输出。
                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
                # 在特定过滤器大小的输出上执行最大化池将留下一张张量[batch_size，1，num_filters]。 这本质上是一个特征向量，其中最后一个维度对应于我们的特征。
                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)
        # 一旦我们从每个过滤器大小得到所有的汇集输出张量，我们将它们组合成一个长形特征向量[batch_size，num_filters_total]。
        # 在tf.reshape中使用-1可以告诉TensorFlow在可能的情况下平坦化维度。
        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
        # tf.nn.xw_plus_b是执行Wx + b矩阵乘法的便利包装器。
        with tf.name_scope('output'):
            W = tf.get_variable('W', shape=[num_filters_total, num_classes],
                                initializer=tf.contrib.layers.xavier_initializer())
            b = tf.Vairable(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.predictions = tf.argmax(self.scores, 1, name='predictions')

        # Calculate mean cross-entropy loss
        with tf.name_scope('loss'):
            losses = tf.nn.softmax_cross_entropy_with_logits(logits=self.scores, labels=self.input_y)
            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')

可视化网络

训练过程

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

# Parameters
# ==================================================

# Data loading params
tf.flags.DEFINE_float("dev_sample_percentage", .1, "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("")

def preprocess():
    # Data Preparation
    # ==================================================

    # Load data
    print("Loading data...")
    x_text, y = data_helpers.load_data_and_labels(FLAGS.positive_data_file, FLAGS.negative_data_file)

    # Build vocabulary
    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)))
    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:]

    del x, y, x_shuffled, y_shuffled

    print("Vocabulary Size: {:d}".format(len(vocab_processor.vocabulary_)))
    print("Train/Dev split: {:d}/{:d}".format(len(y_train), len(y_dev)))
    return x_train, y_train, vocab_processor, x_dev, y_dev

def train(x_train, y_train, vocab_processor, x_dev, y_dev):
    # Training
    # ==================================================

    with tf.Graph().as_default():
        session_conf = tf.ConfigProto(
          allow_soft_placement=FLAGS.allow_soft_placement,
          log_device_placement=FLAGS.log_device_placement)
        sess = tf.Session(config=session_conf)
        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(","))),
                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)
                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, checkpoint_prefix, global_step=current_step)
                    print("Saved model checkpoint to {}\n".format(path))

def main(argv=None):
    x_train, y_train, vocab_processor, x_dev, y_dev = preprocess()
    train(x_train, y_train, vocab_processor, x_dev, y_dev)

if __name__ == '__main__':
    tf.app.run()