Ask Your Question
0

yolo dose not use my GPU [closed]

asked 2018-11-05 21:55:29 -0600

pouya.1991 gravatar image

Hi there, I've installed CUDA 10 on ubuntu 18.04 and compiled both Opencv and darknet with cuda support successfully, but when I wanna to train a yolo network, darknet uses CPU to train the net, what I should do? Is there any other configuration for darknet to use GPU?

edit retag flag offensive reopen merge delete

Closed for the following reason question is off-topic or not relevant by berak
close date 2018-11-06 00:07:05.578775

Comments

As I know darknet has different exe file in GPU and CPU version. Did you use right file?

gino0717 gravatar imagegino0717 ( 2018-11-05 22:55:05 -0600 )edit

we cannot help you to configure darknet from here.

(and it's only using opencv (optionally) for image acquisition / visualization)

berak gravatar imageberak ( 2018-11-06 02:33:35 -0600 )edit

1 answer

Sort by ยป oldest newest most voted
0

answered 2018-11-06 04:05:24 -0600

pouya.1991 gravatar image

Hi thank you for your answers I didn't set GPU=1 in Makefile :X I set this flag and recompiled yolo and it uses gpu now :)

edit flag offensive delete link more

Comments

1

so, we have an answer, at least ;)

berak gravatar imageberak ( 2018-11-06 04:06:45 -0600 )edit

yeah and don't forget to enable CUDNN=1 and OPENCV=1 in the makefile too.

holger gravatar imageholger ( 2020-04-08 06:53:40 -0600 )edit

Question Tools

1 follower

Stats

Asked: 2018-11-05 21:55:29 -0600

Seen: 2,469 times

Last updated: Nov 05 '18