3

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 =[[x 1 1 x 1 2 ,x 1 3 ],...,[x m 1 x m 2 ,x m 3 ]] 并且 x我是一个浮点数。首先，我想训练一个给定序列开始的模型 ([x 1 1 x 1 2 ,x 1 3]) 我可以预测序列的其余部分。然后稍后我希望包含一个分类器来预测每个x i属于哪个二进制类。

所以我的问题是我在模型的开头输入什么并拉出模型的结尾？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，如何完成该__init__功能以使其与我的数据兼容？

4

1 回答 1

7

给定到目前为止从 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：

  • 在完整序列上使用反向传播训练模型 [[x 1 1 x 1 2 ,x 1 3 ],...,[x m 1 x m 2 ,x m 3 ]]
  • 在序列的开头向前运行训练好的模型 [x 1 1 x 1 2 ,x 1 3 ,...] 然后从模型中采样以预测序列的其余部分 [x m 1 x m 2 ,x m 3，...]。

更长的答案是：

您的示例仅显示模型的初始化。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示例函数。

以下代码片段是混合匹配的，仅用于说明目的...

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

例如，在示例代码 tensorflow/models/rnn/ptb_word_lm.py 中，训练循环针对目标（即按一个时间步移动的 input_data）计算批量 input_data 的成本函数

        # 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。（您需要创建一个像这样的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,...]... 向前运行模型以对序列进行预测...此片段假定表示类的二进制值，您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
于 2016-03-10T20:38:10.920 回答