Bidirectionnet_GMM_clustertopK_9000feat.py 文件源码

def sentencenet(self, sentence_emb, reuse=False,skip=False):
        if skip:
            wd = tf.contrib.layers.l2_regularizer(self.weight_decay)
            sentence_fc2 = tf.contrib.layers.fully_connected(self.cluster_feature, 512,activation_fn=None, weights_regularizer=wd, scope='s_fc2')
            sentence_fc2 = sentence_fc2/(tf.norm(sentence_fc2,axis= -1,keep_dims=True)+1e-5)
            self.endpoint['sentence_fc2'] = sentence_fc2
            self.endpoint['cluster'] =self.cluster_feature
            return sentence_fc2
        with tf.variable_scope('sentence_net', reuse=reuse) as scope:
            wd = tf.contrib.layers.l2_regularizer(self.weight_decay)
            sentence_fc1 =tf.nn.dropout(tf.contrib.layers.fully_connected(sentence_emb,2048, \
                                                            weights_regularizer=wd, scope='s_fc1'),keep_prob=self.keep_prob )# 20*10*256
            sentence_fc2 = tf.contrib.layers.fully_connected(tf.concat([sentence_fc1,self.cluster_feature],axis=1), 512,activation_fn=None,normalizer_fn=tf.contrib.layers.batch_norm,\
                                                             normalizer_params={'is_training':self.is_training,'updates_collections':None}, weights_regularizer=wd, scope='s_fc2')
            sentence_fc2 = sentence_fc2/tf.norm(sentence_fc2,axis= -1,keep_dims=True)
        self.endpoint['sentence_fc1'] = sentence_fc1
        self.endpoint['sentence_fc2'] = sentence_fc2
        return sentence_fc2