search

AlexeyAB / darknet

YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet )
http://pjreddie.com/darknet/
Other
21.8k stars 7.97k forks source link

Darknet docker image doesnt work after shipping to another system #4082

Open barzan-hayati opened 5 years ago

barzan-hayati commented 5 years ago

Hi @AlexeyAB . Thanks for your guidance.

First Machine: RTX 2080 Ti with 11G memory Second Machine: Geforce 1050 Ti with 4G memory

I have downloaded a docker image with this specs:cuda9.2.148 cudnn7.5.0 opencv3.4.6 .

Then I pulled darknet and make it.I could successfully train and test tiny-yolov2 and tiny-yolov3 in docker. then I commit this docker container, saved it to a .tar file and moved it to another system. Now I want to test darknet in new system via loading docker image.

When I want to test darknet in new machine, by testing tiny-yolov2 it could not detect any objects and by testing tiny-yolov3 it failed by CUDA Error: out of memory. I think second problem rises for lower GPU memory in second machine. How should I resolve first problem?

Thanks in advance.

dexception commented 5 years ago

Try running it with lower resolution(width, height but with the multiple of 32 by editing the cfg file. Also make sure that these values are batch=1 subdivisions=1

barzan-hayati commented 5 years ago

@dexception your suggestion is for which one? I guess this solution is proper for second one. How about first one?