python darknet_py

[KangminLim]

[yolo] params: iou loss: ciou (4), iou_norm: 0.07, obj_norm: 1.00, cls_norm: 1.00, delta_norm: 1.00, scale_x_y: 1.05 nms_kind: greedynms (1), beta = 0.600000 Total BFLOPS 59.570 avg_outputs = 489910 Allocate additional workspace_size = 22.27 MB Try to load weights: ./backup/yolov4-ANPR.weights Loading weights from ./backup/yolov4-ANPR.weights... seen 64, trained: 256 K-images (4 Kilo-batches_64) Done! Loaded 162 layers from weights-file Loaded - names_list: data/obj.names, classes = 2 Starting the YOLO loop... Segmentation fault (core dumped)

segmentation fault가 발생하신적 없나요 ㅠㅠ?

[gyupro]

https://github.com/gyupro/EasyKoreanLpDetector 이거사용해보세요

[wuyiulin]

I guess it could be cause by you data limit check your YOLO type data It must be limit in 0 - 1 I use np.clip to avoid happen.