Max pooling loss is slow

[robotnc]

I create a model of 100 keywords, and found that the max_pooling loss calculation is very slow. the loss calculation takes 8 second, loss.backward() takes about 16 second per batch(256).
Any plan to improve the speed of this loss ?

[robin1001]

It's a problem if there is so much keywords. We have no bandwith to do it recently.