Hi,
I wanted to understand the purpose of half batch. Prateek bhaiya is saying that we
are taking
Batch_size=256
total _batches=60000/256
And while training on a particular batch we take half images from the Fake Images and Half from the Real images.
So in this way to train on all images we need to take
no_of_btaches=60000/128
Hey @chiragwxN, yes it should be 6000/128. You are right. Although in training that doesn’t make a difference.
Hope this resolved your doubt.
Plz mark the doubt as resolved in my doubts section. 
I hope I’ve cleared your doubt. I ask you to please rate your experience here
Your feedback is very important. It helps us improve our platform and hence provide you
the learning experience you deserve.
On the off chance, you still have some questions or not find the answers satisfactory, you may reopen
the doubt.