a2_transformer.py 文件源码

def __init__(self, num_classes, learning_rate, batch_size, decay_steps, decay_rate, sequence_length,
                 vocab_size, embed_size,d_model,d_k,d_v,h,num_layer,is_training,decoder_sent_length=6,
                 initializer=tf.random_normal_initializer(stddev=0.1),clip_gradients=5.0,l2_lambda=0.0001):
        """init all hyperparameter here"""
        super(Transformer, self).__init__(d_model, d_k, d_v, sequence_length, h, batch_size, num_layer=num_layer) #init some fields by using parent class.

        self.num_classes = num_classes
        self.sequence_length = sequence_length
        self.vocab_size = vocab_size
        self.embed_size = d_model
        self.learning_rate = tf.Variable(learning_rate, trainable=False, name="learning_rate")
        self.learning_rate_decay_half_op = tf.assign(self.learning_rate, self.learning_rate * 0.5)
        self.initializer = initializer
        self.decoder_sent_length=decoder_sent_length
        self.clip_gradients=clip_gradients
        self.l2_lambda=l2_lambda

        self.is_training=is_training #self.is_training=tf.placeholder(tf.bool,name="is_training") #tf.bool #is_training
        self.input_x = tf.placeholder(tf.int32, [self.batch_size, self.sequence_length], name="input_x")                 #x  batch_size
        self.decoder_input = tf.placeholder(tf.int32, [self.batch_size, self.decoder_sent_length],name="decoder_input")  #y, but shift None
        self.input_y_label = tf.placeholder(tf.int32, [self.batch_size, self.decoder_sent_length], name="input_y_label") #y, but shift None
        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() #logits shape:[batch_size,decoder_sent_length,self.num_classes]

        self.predictions = tf.argmax(self.logits, axis=2, name="predictions")
        self.accuracy = tf.constant(0.5)  # fuke accuracy. (you can calcuate accuracy outside of graph using method calculate_accuracy(...) in train.py)
        if self.is_training is False:# if it is not training, then no need to calculate loss and back-propagation.
            return
        self.loss_val = self.loss_seq2seq()
        self.train_op = self.train()