Open yareenm opened 2 years ago
did you try to use other video input? can you share the video?
Is there anyone who had solved this? I have the same problem.
thanks!
Hi, do you use linux or windows? i did switch to linux and it solved a lot of problems. hence maybe you can share the command parameters you used
hi, thank you very much for your reply I'm really sorry that there are some problems with my network, so I directly sent you an email.
I use Windows, and here are the command I use D:\ayolo\darknet\darknet\build\darknet\x64
darknet detector demo cfg/coco.data cfg/yolov4.cfg yolov4.weights data/test.mp4 darknet.exe detector demo cfg\coco.data cfg\yolov4.cfg yolov4.weights data\001.mp4
001 is the video I named myself
Some more detailed error messages ( [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 = 52.43 MB Loading weights from yolov4.weights... seen 64, trained: 32032 K-images (500 Kilo-batches_64) Done! Loaded 162 layers from weights-file video file: data/test.mp4 warning: Error opening file (/build/opencv/modules/videoio/src/cap_ffmpeg_impl.hpp:856) warning: data/test.mp4 (/build/opencv/modules/videoio/src/cap_ffmpeg_impl.hpp:857) [ERROR:0] VIDEOIO(cvCreateCapture_MSMF(filename)): raised unknown C++ exception! )
Thanks again! @kurthorvath
Hey,
I am using yolov4 and darknet. I can do object detection on images but when I do in video I get these errors: -Video-Stream Stopped -Not an option: demo
Here is my command on the Anaconda Prompt: darknet.exe demo data/obj.data cfg/yolov4-obj.cfg backup/yolov4-obj_last.weights walk.mp4 -thresh 0.6
I check the darknet_video.py but I couldn't find the issue.
Thanks