The memory is not fridendly?

[zhangrong1722]

Firstly thank you for your great work. I have a deeper understanding for deformable convolution after reading this script. But I find this version uses huge memory when runs on GPU compared with a cuda version (https://github.com/CharlesShang/DCNv2) . Could you tell me why?

Thank you.

[gf9276]

Excuse me, how did you solve it in the end