TreB1eN/Lighthead-RCNN-in-Pytorch0.4.1

Training is Too Slow

Opened this issue · 1 comments

mmaaz60 commented

Hi @TreB1eN,

While training on COCO with my RTX 2080 Super GPU, it is taking around 20 hours per epoch which is to slow. I mean to run 30 epochs, I need to wait for around 25 days?

How can the training be accelerated? Thanks

lucasjinreal commented

it runs RPN in numpy so speed is slow, you can try using pytorch code to accelerate