p72_TextCNN_with_RCNN_model.py 文件源码

def inference2(self):
        """main computation graph here: 1. embeddding layer, 2.Bi-LSTM layer, 3.max pooling, 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
        output_conv=self.conv_layer_with_recurrent_structure() #shape:[None,sentence_length,embed_size*3]
        #3. max pooling
        #print("output_conv:",output_conv) #(3, 5, 8, 100)
        output_pooling=tf.reduce_max(output_conv,axis=1) #shape:[None,embed_size*3]
        #print("output_pooling:",output_pooling) #(3, 8, 100)
        #4. logits(use linear layer)
        with tf.name_scope("dropout_rcnn"):
            h_drop=tf.nn.dropout(output_pooling,keep_prob=self.dropout_keep_prob) #[None,embed_size*3]

        #with tf.name_scope("output"): #inputs: A `Tensor` of shape `[batch_size, dim]`.  The forward activations of the input network.
            logits = tf.matmul(h_drop, self.W_projection_rcnn) + self.b_projection_rcnn  # [batch_size,num_classes]
        return logits