p8_TextRNN_model.py 文件源码

def inference(self):
        """main computation graph here: 1. embeddding layer, 2.Bi-LSTM layer, 3.concat, 4.FC layer 5.softmax """
        #1.get emebedding of words in the sentence
        self.embedded_words = tf.nn.embedding_lookup(self.Embedding,self.input_x) #shape:[None,sentence_length,embed_size]
        #2. Bi-lstm layer
        # define lstm cess:get lstm cell output
        lstm_fw_cell=rnn.BasicLSTMCell(self.hidden_size) #forward direction cell
        lstm_bw_cell=rnn.BasicLSTMCell(self.hidden_size) #backward direction cell
        if self.dropout_keep_prob is not None:
            lstm_fw_cell=rnn.DropoutWrapper(lstm_fw_cell,output_keep_prob=self.dropout_keep_prob)
            lstm_bw_cell=rnn.DropoutWrapper(lstm_bw_cell,output_keep_prob=self.dropout_keep_prob)
        # bidirectional_dynamic_rnn: input: [batch_size, max_time, input_size]
        #                            output: A tuple (outputs, output_states)
        #                                    where:outputs: A tuple (output_fw, output_bw) containing the forward and the backward rnn output `Tensor`.
        outputs,_=tf.nn.bidirectional_dynamic_rnn(lstm_fw_cell,lstm_bw_cell,self.embedded_words,dtype=tf.float32) #[batch_size,sequence_length,hidden_size] #creates a dynamic bidirectional recurrent neural network
        print("outputs:===>",outputs) #outputs:(<tf.Tensor 'bidirectional_rnn/fw/fw/transpose:0' shape=(?, 5, 100) dtype=float32>, <tf.Tensor 'ReverseV2:0' shape=(?, 5, 100) dtype=float32>))
        #3. concat output
        output_rnn=tf.concat(outputs,axis=2) #[batch_size,sequence_length,hidden_size*2]
        self.output_rnn_last=tf.reduce_mean(output_rnn,axis=1) #[batch_size,hidden_size*2] #output_rnn_last=output_rnn[:,-1,:] ##[batch_size,hidden_size*2] #TODO
        print("output_rnn_last:", self.output_rnn_last) # <tf.Tensor 'strided_slice:0' shape=(?, 200) dtype=float32>
        #4. logits(use linear layer)
        with tf.name_scope("output"): #inputs: A `Tensor` of shape `[batch_size, dim]`.  The forward activations of the input network.
            logits = tf.matmul(self.output_rnn_last, self.W_projection) + self.b_projection  # [batch_size,num_classes]
        return logits