TensorFlow实战12：实现基于LSTM的语言模型

1.LSTM的语言模型简介
LSTM（Long Short Term Memory）,用来处理有时序联系的信息效果非常明显，在很多情况下，卷积神经网络虽然处理图片增加了其空间特征的联系，但是对于图片与图片之间的联系性并不是很强，所以对于视频或者是自然语言处理前后的关联性并不是很好。
对于一些简单的问题，可能只需要最后输入的少量时序信息即可解决问题。但对于复杂问题，可能需要更早的一些信息，甚至是时间序列的开头信息，但间隔太久的信息RNN无法捕获的，所以LSTM的发明就是为了解决这个问题。

如上图所示，LSTM包括了四层神经网络，圆圈是point-wise的操作，比如向量加法、点乘等。小矩形代表一层可学习参数的神经网络。LSTM单元上面的那条直线代表了LSTM的状态state,它会贯穿所有连接在一起的LSTM单元，从第一个LSTM单元一直流向最后一个LSTM单元，其中只有少量的线性干预和改变。状态state在这条隧道中传递时，LSTM单元可以对其添加或者删减信息，这些对信息流的修改操作由LSTM中的Gates控制。这些Gates中包含了一个Sigmoid层和一个向量的点乘的操作，这个Sigmoid层的输出时0到1之间的值，它直接控制了信息传递的比例。如果为0则代表不允许信息传递，如果为1，则表示信息全部通过。每个LSTM单元包含3个这样的Gates，用来维护和控制单元的状态信息。凭借对状态信息的储存和修改，LSTM单元就可以实现长程记忆。
详细的关于RNN和LSTM的信息可以查看http://colah.github.io/posts/2015-08-Understanding-LSTMs/

2.LSTM的语言模型的代码实现
这里和之前有些不一样，需要下载一些数据集，并且要用一些现成的代码来处理数据，所以会稍微有些繁琐。

wget http://www.fit.vutbr.cz/~imikolov/rnnlm/simple-examples.tgztar xvf simple-examples.tgzgit clone https://github.com/tensorflow/models.gitcd models/tutorials/rnn/ptb

#coding:utf-8#导入常用的库，模型中的PTB reader主要是借助它读取数据内容，并把单词转为唯一的数字编码，以便神经网络处理from __future__ import divisionimport time import numpy as npimport tensorflow as tfimport reader#定义语言模型处理输入数据的classclass PTBInput(object):    def __init__(self, config, data, name = None):        self.batch_size = batch_size = config.batch_size        self.num_steps = num_steps = config.num_steps        self.epoch_size = ((len(data) // batch_size) - 1) // num_steps        self.input_data, self.targets = reader.ptb_producer(data, batch_size, num_steps, name = name)#定义语言模型的class,PTBModelclass PTBModel(object):    def __init__(self, is_training, config, input_):        self._input = input_        batch_size = input_.batch_size        num_steps = input_.num_steps        size = config.hidden_size        vocab_size = config.vocab_size#设置默认的LSTM单元        def lstm_cell():            return tf.contrib.rnn.BasicLSTMCell(size, forget_bias = 0.0, state_is_tuple = True)        attn_cell = lstm_cell        if is_training and config.keep_prob < 1:            def attn_cell():                return tf.contrib.rnn.DropoutWrapper(lstm_cell(), output_keep_prob = config.keep_prob)        cell = tf.contrib.rnn.MultiRNNCell([attn_cell() for _ in range(config.num_layers)], state_is_tuple = True)        self._initial_state = cell.zero_state(batch_size, tf.float32)#创建网络的词嵌入的部分        with tf.device("/cpu:0"):            embedding = tf.get_variable("embedding", [vocab_size, size], dtype = tf.float32)            inputs = tf.nn.embedding_lookup(embedding, input_.input_data)        if is_training and config.keep_prob < 1:            inputs = tf.nn.dropout(inputs, config.keep_prob)#定义输出        outputs = []        state = self._initial_state        with tf.variable_scope("RNN"):            for time_step in range(num_steps):                if time_step > 0:tf.get_variable_scope().reuse_variables()                 (cell_output, state) = cell(inputs[:, time_step, :], state)                outputs.append(cell_output)        output = tf.reshape(tf.concat(outputs, 1), [-1, size])        softmax_w = tf.get_variable("softmax_w", [size, vocab_size], dtype = tf.float32)        softmax_b = tf.get_variable("softmax_b", [vocab_size], dtype = tf.float32)        logits = tf.matmul(output, softmax_w) + softmax_b        loss = tf.contrib.legacy_seq2seq.sequence_loss_by_example([logits], [tf.reshape(input_.targets, [-1])],                                                                    [tf.ones([batch_size * num_steps], dtype = tf.float32)])        self._cost = cost = tf.reduce_sum(loss) / batch_size        self._final_state = state        if not is_training:            return#定义学习率，优化器等        self._lr = tf.Variable(0.0, trainable = False)        tvars = tf.trainable_variables()        grads, _ = tf.clip_by_global_norm(tf.gradients(cost, tvars), config.max_grad_norm)        optimizer = tf.train.GradientDescentOptimizer(self._lr)        self._train_op = optimizer.apply_gradients(zip(grads, tvars),            global_step = tf.contrib.framework.get_or_create_global_step())        self._new_lr = tf.placeholder(tf.float32, shape = [], name = "new_learning_rate")        self._lr_update = tf.assign(self._lr, self._new_lr)    def assign_lr(self, session, lr_value):        session.run(self._lr_update, feed_dict = {self._new_lr: lr_value})#利用@property装饰器可以将返回变量设为只读    @property    def input(self):        return self._input    @property    def initial_state(self):        return self._initial_state    @property    def cost(self):        return self._cost    @property    def final_state(self):        return self._final_state    @property    def lr(self):        return self._lr    @property    def train_op(self):        return self._train_op#定义小的训练模型参数class SmallConfig(object):    init_scale = 0.1    learning_rate = 1.0    max_grad_norm = 5    num_layers = 2    num_steps = 20    hidden_size = 200    max_epoch = 4    max_max_epoch = 13    keep_prob = 1.0    lr_decay = 0.5    batch_size = 20    vocab_size = 10000#定义中等的训练模型参数class MediumConfig(object):    init_scale = 0.05    learning_rate = 1.0    max_grad_norm = 5    num_layers = 2    num_steps = 35    hidden_size = 650    max_epoch = 6    max_max_epoch = 39    keep_prob = 0.5    lr_decay = 0.8    batch_size = 20    vocab_size = 10000#定义大的训练模型参数class LargeConfig(object):    init_scale = 0.04    learning_rate = 1.0    max_grad_norm = 10    num_layers = 2    num_steps = 35    hidden_size = 1500    max_epoch = 14    max_max_epoch = 55    keep_prob = 0.35    lr_decay = 1 / 1.15    batch_size = 20    vocab_size = 10000#定义测试时的训练模型class TestConfig(object):    init_scale = 0.1    learning_rate = 1.0    max_grad_norm = 1    num_layers = 1    num_steps = 2    hidden_size = 2    max_epoch = 1    max_max_epoch = 1    keep_prob = 1.0    lr_decay = 0.5    batch_size = 20    vocab_size = 10000#定义训练一个epoch数据的函数def run_epoch(session, model, eval_op = None, verbose = False):    start_time = time.time()    costs = 0.0    iters = 0    state = session.run(model.initial_state)    fetches = {            "cost": model.cost,            "final_state": model.final_state,            }    if eval_op is not None:        fetches["eval_op"] = eval_op    for step in range(model.input.epoch_size):        feed_dict = {}        for i, (c, h) in enumerate(model.initial_state):            feed_dict[c] = state[i].c            feed_dict[h] = state[i].h        vals = session.run(fetches, feed_dict)        cost = vals["cost"]        state = vals["final_state"]        costs += cost        # print cost        iters += model.input.num_steps        if verbose and step % (model.input.epoch_size // 10) == 10:            print ("%.3f perplexity: %.3f speed : %.0f wps"                 %(step * 1.0 / model.input.epoch_size, np.exp(costs / iters),                 iters * model.input.batch_size / (time.time() - start_time)))    return np.exp(costs / iters)#直接读取解压数据raw_data = reader.ptb_raw_data('simple-examples/data/')train_data, valid_data, test_data, _ = raw_dataconfig = SmallConfig()eval_config = SmallConfig()eval_config.batch_size = 1eval_config.num_steps = 1#创建图with tf.Graph().as_default():    initializer = tf.random_uniform_initializer(-config.init_scale, config.init_scale)    with tf.name_scope("Train"):        train_input = PTBInput(config = config, data = train_data, name = 'TrainInput')        with tf.variable_scope("Model", reuse = None, initializer = initializer):            m = PTBModel(is_training = True, config = config, input_ = train_input)    with tf.name_scope("Valid"):        valid_input = PTBInput(config = config, data = valid_data, name = "ValidInput")        with tf.variable_scope("Model", reuse = True, initializer = initializer):            mvalid = PTBModel(is_training = False, config = config, input_ = valid_input)    with tf.name_scope("Test"):        test_input = PTBInput(config = eval_config, data = test_data, name = "TestInput")        with tf.variable_scope("Model", reuse = True, initializer = initializer):            mtest = PTBModel(is_training = False, config = eval_config, input_ = test_input)#创建训练的管理器        sv = tf.train.Supervisor()        with sv.managed_session() as session:            for i in range(config.max_max_epoch):                lr_decay = config.lr_decay ** max(i + 1 - config.max_epoch, 0.0)                m.assign_lr(session, config.learning_rate * lr_decay)                print("Epoch: %d Learning rate: %.3f" %(i + 1, session.run(m.lr)))                train_perplexity = run_epoch(session, m, eval_op = m.train_op, verbose = True)                print("Epoch: %d Train Perplexity: %.3f" %(i + 1, train_perplexity))                valid_perplexity = run_epoch(session, mvalid)                print("Epoch: %d valid Perplexity: %.3f" %(i + 1, valid_perplexity))            test_perplexity = run_epoch(session, mtest)            print("Test Perplexity: %.3f" %test_perplexity)

我只想说这个编辑器有bug，回车会自动把代码删除。。。这是什么鬼？O(∩_∩)O