a2_transformer_classification.py 文件源码

def loss(self, l2_lambda=0.0001):  # 0.001
        with tf.name_scope("loss"):
            # input: `logits`:[batch_size, num_classes], and `labels`:[batch_size]
            # output: A 1-D `Tensor` of length `batch_size` of the same type as `logits` with the softmax cross entropy loss.
            losses = tf.nn.sparse_softmax_cross_entropy_with_logits(labels=self.input_y_label,logits=self.logits);  # sigmoid_cross_entropy_with_logits.#losses=tf.nn.softmax_cross_entropy_with_logits(labels=self.input_y,logits=self.logits)
            # print("1.sparse_softmax_cross_entropy_with_logits.losses:",losses) # shape=(?,)
            loss = tf.reduce_mean(losses)  # print("2.loss.loss:", loss) #shape=()
            l2_losses = tf.add_n([tf.nn.l2_loss(v) for v in tf.trainable_variables() if ('bias' not in v.name ) and ('alpha' not in v.name)]) * l2_lambda
            loss = loss + l2_losses
        return loss

    #def loss_seq2seq(self):
    #    with tf.variable_scope("loss"):
    #        losses = tf.nn.sparse_softmax_cross_entropy_with_logits(labels=self.input_y_label, logits=self.logits);#losses:[batch_size,self.decoder_sent_length]
    #        loss_batch=tf.reduce_sum(losses,axis=1)/self.decoder_sent_length #loss_batch:[batch_size]
    #        loss=tf.reduce_mean(loss_batch)
    #        l2_losses = tf.add_n([tf.nn.l2_loss(v) for v in tf.trainable_variables() if 'bias' not in v.name]) * self.l2_lambda
    #        loss = loss + l2_losses
    #        return loss