Keras-RetinaNet-for-Open-Images-Challenge-2018 icon indicating copy to clipboard operation
Keras-RetinaNet-for-Open-Images-Challenge-2018 copied to clipboard

Published 20 hours ago • verified publisher icon ZFTurbo

Hi, how to use multi gpus?

Open louielu1027 opened this issue 6 years ago • 2 comments

I use 8 gpus for infenrence, but it is slowly than 1 gpu...... I changed 'gpu_use = 0' to 'gpu_use = 0,1,2,3,4,5,6,7' in retinanet_inference_example.py. Is it right?

louielu1027 avatar Sep 26 '19 03:09 louielu1027

No, this variable only controls which GPU use for calculation. Code is for single GPU only. If you need inference on several GPU, just split data in N parts and run inference in parallel on each of them.

ZFTurbo avatar Sep 26 '19 07:09 ZFTurbo

Ok, Thanks!

louielu1027 avatar Sep 26 '19 07:09 louielu1027