如何在Tensorflow中结合FCNN和RNN？

Question

我想制作一个神经网络，它会在某些层次上具有重复性（例如LSTM），在其他层次上具有正常连接（FC）。 我无法在Tensorflow中找到一种方法。 它的工作原理，如果我只有FC层，但我不知道如何恰当地添加一个经常性图层。

我在下面的方式建立网络

with tf.variable_scope("autoencoder_variables", reuse=None) as scope: 

    for i in xrange(self.__num_hidden_layers + 1): 
    # Train weights 
    name_w = self._weights_str.format(i + 1) 
    w_shape = (self.__shape[i], self.__shape[i + 1]) 
    a = tf.multiply(4.0, tf.sqrt(6.0/(w_shape[0] + w_shape[1]))) 
    w_init = tf.random_uniform(w_shape, -1 * a, a) 
    self[name_w] = tf.Variable(w_init, 
           name=name_w, 
           trainable=True) 
    # Train biases 
    name_b = self._biases_str.format(i + 1) 
    b_shape = (self.__shape[i + 1],) 
    b_init = tf.zeros(b_shape) 
    self[name_b] = tf.Variable(b_init, trainable=True, name=name_b) 

    if i+1 == self.__recurrent_layer: 
     # Create an LSTM cell 
     lstm_size = self.__shape[self.__recurrent_layer] 
     self['lstm'] = tf.contrib.rnn.BasicLSTMCell(lstm_size) 

应该处理的批次顺序排列。我有处理只是一个时间步长的函数，这将在稍后调用，通过一个函数，该函数处理整个序列：

def single_run(self, input_pl, state, just_middle = False): 
    """Get the output of the autoencoder for a single batch 

    Args: 
    input_pl:  tf placeholder for ae input data of size [batch_size, DoF] 
    state:  current state of LSTM memory units 
    just_middle : will indicate if we want to extract only the middle layer of the network 
    Returns: 
    Tensor of output 
    """ 

    last_output = input_pl 

    # Pass through the network 
    for i in xrange(self.num_hidden_layers+1): 

    if(i!=self.__recurrent_layer): 
     w = self._w(i + 1) 
     b = self._b(i + 1) 
     last_output = self._activate(last_output, w, b) 

    else: 
     last_output, state = self['lstm'](last_output,state) 

    return last_output 

下面的函数应该采取分批作为输入序列，并产生批次的序列作为输出：

def process_sequences(self, input_seq_pl, dropout, just_middle = False): 
    """Get the output of the autoencoder 

    Args: 
    input_seq_pl:  input data of size [batch_size, sequence_length, DoF] 
    dropout:   dropout rate 
    just_middle :  indicate if we want to extract only the middle layer of the network 
    Returns: 
    Tensor of output 
    """ 

    if(~just_middle): # if not middle layer 
    numb_layers = self.__num_hidden_layers+1 
    else: 
    numb_layers = FLAGS.middle_layer 

    with tf.variable_scope("process_sequence", reuse=None) as scope: 

    # Initial state of the LSTM memory. 
    state = initial_state = self['lstm'].zero_state(FLAGS.batch_size, tf.float32) 

    tf.get_variable_scope().reuse_variables() # THIS IS IMPORTANT LINE 

    # First - Apply Dropout 
    the_whole_sequences = tf.nn.dropout(input_seq_pl, dropout) 

    # Take batches for every time step and run them through the network 
    # Stack all their outputs 
    with tf.control_dependencies([tf.convert_to_tensor(state, name='state') ]): # do not let paralelize the loop 
     stacked_outputs = tf.stack([ self.single_run(the_whole_sequences[:,time_st,:], state, just_middle) for time_st in range(self.sequence_length) ]) 

    # Transpose output from the shape [sequence_length, batch_size, DoF] into [batch_size, sequence_length, DoF] 

    output = tf.transpose(stacked_outputs , perm=[1, 0, 2]) 

    return output 

问题是变量作用域及其属性“重用”。

如果我按照原样运行此代码，则会收到以下错误： '变量列车/过程_序列/基本_lstm_cell /权重不存在，或者未使用tf.get_variable（）创建。你是否想在VarScope中设置重用=无？ “

如果我注释掉线，告诉它重用变量我收到以下错误（tf.get_variable_scope（）reuse_variables（）。）： ”变量火车/ process_sequence/basic_lstm_cell /权重已经存在，不允许。你是否想在VarScope中设置reuse = True？'

看来，我们需要“重用=无”来初始化LSTM单元的权重，我们需要“reuse = True”来调用LSTM单元。

请帮助我找出正确的方法。

Answer 1

看来，我已经解决了利用Tensorflow RNN官方的例子（https://www.tensorflow.org/tutorials/recurrent）黑客用下面的代码这个问题

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) 

的黑客是，当我们运行LSTM第一次，tf.get_variable_scope（ ）.reuse设置为False，以便创建新的LSTM单元。当我们下次运行它时，我们将tf.get_variable_scope（）。reuse设置为True，以便我们使用已创建的LSTM。

Answer 2

我认为问题在于你正在用tf.Variable创建变量。请改用tf.get_variable - 这是否解决了您的问题？