用YOLOv5模型对流媒体和网络视频做推理的时候发生了报错——OSError: [WinError 123] 文件名、目录名或卷标语法不正确。
以下是终端中的信息
(pyyolo) D:\YOLOv5\yolov5-6.2>python detect.py --source rtsp://example.com/media.mp4 --view-img --weights runs/train/exp8/weights/best.pt
detect: weights=['runs/train/exp8/weights/best.pt'], source=rtsp://example.com/media.mp4, data=data\coco128.yaml, imgsz=[640, 640], conf_thres=0.25, iou_thres=0.45, max_det=1000, device=, view_img=True, save_txt=False, save_conf=False,
save_crop=False, nosave=False, classes=None, agnostic_nms=False, augment=False, visualize=False, update=False, project=runs\detect, name=exp, exist_ok=False, line_thickness=3, hide_labels=False, hide_conf=False, half=False, dnn=False
Traceback (most recent call last):
File "detect.py", line 276, in <module>
main(opt)
File "detect.py", line 252, in main
run(**vars(opt))
File "D:\anconda\envs\pyyolo\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "detect.py", line 85, in run
source = check_file(source) # download
File "D:\YOLOv5\yolov5-6.2\utils\general.py", line 434, in check_file
if Path(file).is_file() or not file: # exists
File "D:\anconda\envs\pyyolo\lib\pathlib.py", line 1420, in is_file
return S_ISREG(self.stat().st_mode)
File "D:\anconda\envs\pyyolo\lib\pathlib.py", line 1194, in stat
return self._accessor.stat(self)
OSError: [WinError 123] 文件名、目录名或卷标语法不正确。: 'rtsp:\\example.com\\media.mp4'
我看readme 中是这样对流媒体进行检测的啊，而且这个链接我试过可以直接打开
改斜杠啥得都试过了，但无论是http还是rtsp等等都有这个报错，本地视频和图片还有摄像头都能正常检测
