python - Tensorflow 的 LSTM 输入

Question

我正在尝试在 Tensorflow 中创建一个 LSTM 网络，但我迷失了术语/基础知识。我有 n 个时间序列示例，所以 X=x_n，其中x_i=[[x₁¹x₁²,x₁³],...,[x_m¹x_m ²,x_m³]] 其中 x_iⁱ 是一个 float 。首先，我想训练一个给定序列开始的模型 ([x₁¹x₁²,x₁³]) 我可以预测序列的其余部分。然后我希望包括一个分类器来预测每个 x_i 属于哪个二进制类。

所以我的问题是我应该在模型的开头输入什么，然后从模型的结尾拉出什么？到目前为止，我有一些看起来像下面的东西

class ETLSTM(object):
    """docstring for ETLSTM"""
    def __init__(self, isTraining, config):
        super(ETLSTM, self).__init__()

        # This needs to be tidied
        self.batchSize = batchSize = config.batchSize
        self.numSteps = numSteps = config.numSteps
        self.numInputs = numInputs = config.numInputs
        self.numLayers = numLayers = config.numLayers

        lstmSize = config.lstm_size
        DORate = config.keep_prob

        self.input_data = tf.placeholder(tf.float32, [batchSize, numSteps,
                                                      numInputs])
        self.targets = tf.placeholder(tf.float32, [batchSize, numSteps,
                                                   numInputs])
        lstmCell = rnn_cell.BasicLSTMCell(lstmSize, forgetbias=0.0)
        if(isTraining and DORate < 1):
            lstmCell = tf.nn.rnn_cell.DropoutWrapper(lstmCell,
                                                     output_keep_prob=DORate)
        cell = tf.nn.rnn_cell.MultiRNNCell([lstmCell]*numLayers)

        self._initial_state = cell.zero_state(batchSize, tf.float32)

        # This won't work with my data, need to find what goes in...
        with tf.device("/cpu:0"):
            embedding = tf.get_variable("embedding", [vocab_size, size])
            inputs = tf.nn.embedding_lookup(embedding, self._input_data)

        if(isTraining and DORate < 1):
            inputs = tf.nn.dropout(inputs, DORate)

编辑:具体来说，如何完成 __init__ 函数，使其与我的数据兼容？

Answer 1

到目前为止，给定从 1 到 N 的值，RNN 预测 N+1 的值。 (LSTM 只是实现 RNN 单元的一种方法。)

简短的回答是:

• 使用完整序列的反向传播训练模型 [[x₁¹x₁², x₁³],...,[x_m¹x_m ²,x_m³]]
• 在序列 [x₁¹x₁² 的开始向前运行训练好的模型， x₁³,...] 然后从模型中采样以预测序列的其余部分 [x_m¹x_m²,x_m³,...]。

较长的答案是:

您的示例仅显示了模型的初始化。您还需要实现一个训练函数来运行反向传播以及一个预测结果的样本函数。

以下代码片段是混合搭配的，仅供说明之用...

对于训练，只需在数据迭代器中使用 start + rest 输入完整序列即可。

例如，在示例代码 tensorflow/models/rnn/ptb_word_lm.py 中，训练循环计算针对目标的批量输入数据的成本函数(这是按一个时间步移动的输入数据)

        # compute a learning rate decay
        session.run(tf.assign(self.learning_rate_variable, learning_rate))

        logger.info("Epoch: %d Learning rate: %.3f" % (i + 1, session.run(self.learning_rate_variable)))


        """Runs the model on the given data."""
        epoch_size = ((len(training_data) // self.batch_size) - 1) // self.num_steps
        costs = 0.0
        iters = 0
        state = self.initial_state.eval()
        for step, (x, y) in enumerate(self.data_iterator(training_data, self.batch_size, self.num_steps)):

            # x and y should have shape [batch_size, num_steps]
            cost, state, _ = session.run([self.cost_function, self.final_state, self.train_op],
                                     {self.input_data: x,
                                      self.targets: y,
                                      self.initial_state: state})
            costs += cost
            iters += self.num_steps

请注意，tensorflow/models/rnn/reader.py 中的数据迭代器将输入数据返回为“x”，将目标返回为“y”，它们只是从 x 向前移动了一步。 (您需要像这样创建一个数据迭代器来打包您的训练序列集。)

def ptb_iterator(raw_data, batch_size, num_steps):
  raw_data = np.array(raw_data, dtype=np.int32)

  data_len = len(raw_data)
  batch_len = data_len // batch_size
  data = np.zeros([batch_size, batch_len], dtype=np.int32)
  for i in range(batch_size):
    data[i] = raw_data[batch_len * i:batch_len * (i + 1)]

  epoch_size = (batch_len - 1) // num_steps

  if epoch_size == 0:
    raise ValueError("epoch_size == 0, decrease batch_size or num_steps")

  for i in range(epoch_size):
    x = data[:, i*num_steps:(i+1)*num_steps]
    y = data[:, i*num_steps+1:(i+1)*num_steps+1]
    yield (x, y)

训练后，您通过输入序列的开头 start_x=[X1, X2, X3,...] 来向前运行模型以对序列进行预测...此片段假定二进制值表示类，您d 必须调整浮点值的采样函数。

def sample(self, sess, num=25, start_x):

    # return state tensor with batch size 1 set to zeros, eval
    state = self.rnn_layers.zero_state(1, tf.float32).eval()

    # run model forward through the start of the sequence
    for char in start_x:

        # create a 1,1 tensor/scalar set to zero
        x = np.zeros((1, 1))

        # set to the vocab index
        x[0, 0] = char


        # fetch: final_state
        # input_data = x, initial_state = state
        [state] = sess.run([self.final_state], {self.input_data: x, self.initial_state:state})

    def weighted_pick(weights):

        # an array of cummulative sum of weights
        t = np.cumsum(weights)

        # scalar sum of tensor
        s = np.sum(weights)

        # randomly selects a value from the probability distribution
        return(int(np.searchsorted(t, np.random.rand(1)*s)))

    # PREDICT REST OF SEQUENCE
    rest_x = []

    # get last character in init
    char = start_x[-1]

    # sample next num chars in the sequence after init
    score = 0.0

    for n in xrange(num):

        # init input to zeros
        x = np.zeros((1, 1))

        # lookup character index
        x[0, 0] = char

        # probs = tf.nn.softmax(self.logits)
        # fetch: probs, final_state
        # input_data = x, initial_state = state
        [probs, state] = sess.run([self.output_layer, self.final_state], {self.input_data: x, self.initial_state:state})

        p = probs[0]
        logger.info("output=%s" % np.shape(p))
        # sample = int(np.random.choice(len(p), p=p))

        # select a random value from the probability distribution
        sample = weighted_pick(p)
        score += p[sample]
        # look up the key with the index
        logger.debug("sample[%d]=%d" % (n, sample))
        pred = self.vocabulary[sample]
        logger.debug("pred=%s" % pred)

        # add the car to the output
        rest_x.append(pred) 

        # set the next input character
        char = pred
    return rest_x, score