How does batch norm behave in pytorch depending if one is in training mode or eval/inference mode?

[Brando_Miranda (MirandaAgent)]

How does pytorch’s batch norm know if the forward pass its doing is for inference or training?

how does pytorch’s batch norm know if the forward pass its doing is for inference or training? I am evaluating the the test performance of my net but realized that I’m not sure how my net knows if its training phase or inference phase. How does pytorch handle this?