p9_twoCNNTextRelation_model.py 文件源码

def __init__(self, filter_sizes,num_filters,num_classes, learning_rate, batch_size, decay_steps, decay_rate,sequence_length,vocab_size,
                 embed_size,is_training,initializer=tf.random_normal_initializer(stddev=0.1)):
        """init all hyperparameter here"""
        # set hyperparamter
        self.num_classes = num_classes
        self.batch_size = batch_size
        self.sequence_length=sequence_length
        self.vocab_size=vocab_size
        self.embed_size=embed_size
        self.is_training=is_training
        self.learning_rate=learning_rate
        self.filter_sizes=filter_sizes # it is a list of int. e.g. [3,4,5]
        self.num_filters=num_filters
        self.initializer=initializer
        self.num_filters_total=self.num_filters * len(filter_sizes) #how many filters totally.

        # add placeholder (X,label)
        self.input_x = tf.placeholder(tf.int32, [None, self.sequence_length], name="input_x")  # X: first sentence
        self.input_x2 = tf.placeholder(tf.int32, [None, self.sequence_length], name="input_x2")  # X: second sentence
        self.input_y = tf.placeholder(tf.int32, [None,],name="input_y")  # y: 0 or 1. 1 means two sentences related to each other;0 means no relation.
        self.dropout_keep_prob=tf.placeholder(tf.float32,name="dropout_keep_prob")

        self.global_step = tf.Variable(0, trainable=False, name="Global_Step")
        self.epoch_step=tf.Variable(0,trainable=False,name="Epoch_Step")
        self.epoch_increment=tf.assign(self.epoch_step,tf.add(self.epoch_step,tf.constant(1)))
        self.decay_steps, self.decay_rate = decay_steps, decay_rate
        self.instantiate_weights()
        self.logits = self.inference() #[None, self.label_size]. main computation graph is here.
        if not is_training:
            return
        self.loss_val = self.loss()
        self.train_op = self.train()
        self.predictions = tf.argmax(self.logits, 1, name="predictions")  # shape:[None,]

        correct_prediction = tf.equal(tf.cast(self.predictions,tf.int32), self.input_y) #tf.argmax(self.logits, 1)-->[batch_size]
        self.accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32), name="Accuracy") # shape=()