search

pjreddie / darknet

Convolutional Neural Networks
http://pjreddie.com/darknet/
Other
25.73k stars 21.33k forks source link

Segmentation Fault on Raspberry Pi 3 #1361

Open Flock1 opened 5 years ago

Flock1 commented 5 years ago

Hi,

I am trying to run Tiny YOLO v3 on raspberry pi 3 (raspbian) and I'm getting the following:

Loading weights from yolov3-tiny.weights...Done!
data/dog.jpg: Predicted in 32.183086 seconds.
Segmentation fault

I am running YOLO on the dog image. So can someone help me how to overcome this?

PeterQuinn925 commented 5 years ago

I haven't had a lot of success using Yolo on Raspberry's. They're too slow and don't have enough memory. I bought a Jevois to run the Yolo code for my Raspi project.

Favi0 commented 5 years ago

check out this https://github.com/zxzhaixiang/darknet-nnpack

ljh14 commented 5 years ago

Hello, have you solve this problem? I also came across this problem. And I run the model well in the GPU server.