pjreddie / darknet

Convolutional Neural Networks
http://pjreddie.com/darknet/
Other
25.87k stars 21.33k forks source link

Unable to run Tiny yolo v3 on Jetson TX1 #958

Open Joeng22 opened 6 years ago

Joeng22 commented 6 years ago

Hey,

I am trying to run darknet tiny yolo v3 object detection in jetson TX1 with jetpack 3.2 along with CUDA 9. But it is unable to detect the object. However it is working fine on my TX1 with jetpack 3.1. Kindly let me know, what changes I have to make it up and running with jetpack 3.2. Output obtained after running this ./darknet detect cfg/yolov3-tiny.cfg yolov3-tiny.weights data/dog.jpg

Loading weights from yolov3.weights...Done! data/dog.jpg: Predicted in 0.293671 seconds. Segmentation fault

Thanks

jingtianyilong commented 6 years ago

got a tx2. I've met this "segmentation fault" when I use the wrong cfg file or wrong weights file. Or simply, the weights file is damaged. I would check that first