What's the meaning of gain in initial


what is the meaning of the gain?
what‘s the differences between gain=1 and gain=sqrt(2)


This is explained in the doc for init.calculate_gain.

thank you.i have saw the doc, however i really do not know how it works


From what I remember, It is just a heuristic that depends on the non linearity.
It represent roughly how the non linearity scale the outputs and by using this information, you can initialize your weights in a better way. To make sure your network will keep everything at roughtly the same scale.