search

CharlesShang / DCNv2

Deformable Convolutional Networks v2 with Pytorch
BSD 3-Clause "New" or "Revised" License
1.28k stars 402 forks source link

training speed is slow #56

Open Hub-Tian opened 4 years ago

Hub-Tian commented 4 years ago

When I change traditional conv with deformable conv, the training speed is 10✖ times lower than before with a vgg backbone. my pytorch version is v1.1 and my cuda is v10.1. Anyone knows how to improve the speed?

hua-wu-que commented 4 years ago

Hi,

Did you still suffer from low speed?