Train-YOLOv3-with-OpenImagesV4
Train-YOLOv3-with-OpenImagesV4 copied to clipboard
Segmentation fault, but unlike any other
Sooo, here is my issue:
bi@Nvidia-Learning ~/darknet $ ./darknet detect cfg/deer.data cfg/deer.cfg ../backup/deer_10000.weights ../trailcam_images/rYB688x3wvZtB2Y3GY5McKv25ip43Ms01NMgv5VG.jpeg
Segmentation fault
If I exclude the cfg/deer.data
then it runs fine and detects what I need, however the label is wrong. Any idea what could have gone wrong?
Other:
I think I've "over-teached" my system and now I have weight files from deer_100.weights
to deer_430000.weights
. Seemingly the best file to work with it deer_10000.weights
. Is there any way also to determine when should I stop the teaching?