How can we find and manage the number of neurons in each Conv layer? Is it equal to number of filters?
Backend MLP formation
Hey manas,
It’s not necessary to keep no of neurons and filters same in the layer. These both are called hyper parameters and there are no specific hard-fast rule to choose these params you can use any no you want, but that should not make your model overfit or underfit.
We generally take a factor of 2. like 32, 64 etc.
Thanks 
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.