Hello,
Thank you for this repository, I have two questions, the first is how can I use your model on webcam, I mean instead of using args ( video file ), I would like to use my webcam
I'm trying changing this line:
vid = cv2.VideoCapture(args.input_video)
to
vid= cv2.VideoCapture(0)
and comment on the two lines of args ( video file ). But I didn't get any results and any error.
just in the last line a simple message and no frame.
[ WARN:0] terminating async callback
The second is how can I speed the video output:
I'm trying a simple trick, reduce the size of the input video from (416,416) to (100,100)
the value of speed ms changes from 360 ms to 152 ms , that was a good way to speed the fps but with some not good predictions ( object detection).
Can you give me a solution to the two problems?
Hello, Thank you for this repository, I have two questions, the first is how can I use your model on webcam, I mean instead of using args ( video file ), I would like to use my webcam I'm trying changing this line:
to
and comment on the two lines of args ( video file ). But I didn't get any results and any error. just in the last line a simple message and no frame.
The second is how can I speed the video output:
the value of speed ms changes from 360 ms to 152 ms , that was a good way to speed the fps but with some not good predictions ( object detection). Can you give me a solution to the two problems?
System information: