AlexeyAB / darknet

YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet )
http://pjreddie.com/darknet/
Other
21.77k stars 7.96k forks source link

CUDA status Error: file: .../src/convolutional_kernels.cu : () : line: 138 #8652

Open yycchao opened 2 years ago

yycchao commented 2 years ago

[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 128.459 avg_outputs = 1068395 Allocate additional workspace_size = 26.62 MB Try to load weights: /opt/project/weights/yolov4.weights Loading weights from /opt/project/weights/yolov4.weights... seen 64, trained: 32032 K-images (500 Kilo-batches_64) CUDA status Error: file: /home/xcj/XCJidenpeople/darknet-compile/src/convolutional_kernels.cu : () : line: 138 : build time: Aug 31 2022 - 09:35:12

CUDA Error: invalid device function Darknet error location: /home/xcj/XCJidenpeople/darknet-compile/src/dark_cuda.c, check_error, line #69 CUDA Error: invalid device function: Success

yycchao commented 2 years ago

I need help! This problem has troubled me for many days. Thanks a lot. my environment is : ubuntu 20.04 cuda 11.1 nvidia-driver 470.141.03 cudnn 8.2.0.53 gcc 9.4.0

cenit commented 2 years ago

can you please describe your build steps?