Why the GPU memory of rednet50 is larger than resnet50?

[yushanshan05]

I used Tesla V100.
When I train resnet50-retinanet, the gpu memory is 9.26G.
But when I train rednet50-retinanet, the gpu memory is 10.98G.
In your paper, the params and floats of rednet50 is less than resnet50.

I only change resnet50 to rednet50, don't change the neck, the head, the input size and other params.
I don't know why. I expect for your reply

[xiaoshuomin]

I have the same problem.Rednet50 needs larger gpu memory.Have you solved the problem?