If the consistency term should operate on the instance data rather than on the batch data?

[ctc53]

Hi, I wonder if this code snippet is an issue:
"CT_ = tf.reduce_mean(CT_)" operates on the batch data.
Is it proper to change it to "CT_ = tf.reduce_mean(CT_)[0]" to operate on the first instance.

https://github.com/biuyq/CT-GAN/blob/master/CT-GANs/tensorflow_generative_model/CT_gan_cifar_resnet.py
#consistency term
CT = LAMBDA_2tf.square(disc_real-disc_real_)
CT += LAMBDA_20.1tf.reduce_mean(tf.square(disc_real_2-disc_real_2_),reduction_indices=[1])
CT_ = tf.maximum(CT-Factor_M,0.0(CT-Factor_M))
CT_ = tf.reduce_mean(CT_) <-----
disc_costs.append(CT_)
disc_costs.append(gradient_penalty)