RNN_Model.py 文件源码

def __init__(self, vocabularySize, config_param):
    self.vocabularySize = vocabularySize
    self.config = config_param

    self._inputX = tf.placeholder(tf.int32, [self.config.batch_size, self.config.sequence_size], "InputsX")
    self._inputTargetsY = tf.placeholder(tf.int32, [self.config.batch_size, self.config.sequence_size], "InputTargetsY")


    #Converting Input in an Embedded form
    with tf.device("/cpu:0"): #Tells Tensorflow what GPU to use specifically
      embedding = tf.get_variable("embedding", [self.vocabularySize, self.config.embeddingSize])
      embeddingLookedUp = tf.nn.embedding_lookup(embedding, self._inputX)
      inputs = tf.split(1, self.config.sequence_size, embeddingLookedUp)
      inputTensorsAsList = [tf.squeeze(input_, [1]) for input_ in inputs]


    #Define Tensor RNN
    singleRNNCell = rnn_cell.BasicRNNCell(self.config.hidden_size)
    self.multilayerRNN =  rnn_cell.MultiRNNCell([singleRNNCell] * self.config.num_layers)
    self._initial_state = self.multilayerRNN.zero_state(self.config.batch_size, tf.float32)

    #Defining Logits
    hidden_layer_output, last_state = rnn.rnn(self.multilayerRNN, inputTensorsAsList, initial_state=self._initial_state)
    hidden_layer_output = tf.reshape(tf.concat(1, hidden_layer_output), [-1, self.config.hidden_size])
    self._logits = tf.nn.xw_plus_b(hidden_layer_output, tf.get_variable("softmax_w", [self.config.hidden_size, self.vocabularySize]), tf.get_variable("softmax_b", [self.vocabularySize]))
    self._predictionSoftmax = tf.nn.softmax(self._logits)

    #Define the loss
    loss = seq2seq.sequence_loss_by_example([self._logits], [tf.reshape(self._inputTargetsY, [-1])], [tf.ones([self.config.batch_size * self.config.sequence_size])], self.vocabularySize)
    self._cost = tf.div(tf.reduce_sum(loss), self.config.batch_size)

    self._final_state = last_state