Thanks for pointing out anomaly detection! This was very helpful in finding where nans were coming from in my custom loss function. Protip: adding a tiny epsilon where you’re dividing or taking square roots will probably do the trick.
Thanks for pointing out anomaly detection! This was very helpful in finding where nans were coming from in my custom loss function. Protip: adding a tiny epsilon where you’re dividing or taking square roots will probably do the trick.