我想用RTMP上的YOLO实时检测对象。 我已经使用过:https://github.com/MarcoBay/darknet-rtmp 但是当我使用它时,错误发生如下:
*darknet.exe detector demo cfg/coco.data yolo.cfg yolov3_gpu_4000.weights -dont_show -rtmp_fps 15 -rtmp_bps 2000000 rtmp://192.168.110.48:1935/live/001*
Demo
layer filters size input output
0 TH conv 32 3 x 3 / 1 608 x 608 x 3 -> 608 x 608 x 32
1 TH conv 64 3 x 3 / 2 608 x 608 x 32 -> 304 x 304 x 64
2 TH conv 32 1 x 1 / 1 304 x 304 x 64 -> 304 x 304 x 32
3 TH conv 64 3 x 3 / 1 304 x 304 x 32 -> 304 x 304 x 64
4 Shortcut Layer: 1
...
95 route 91
96 TH conv 128 1 x 1 / 1 38 x 38 x 256 -> 38 x 38 x 128
97 upsample 2x 38 x 38 x 128 -> 76 x 76 x 128
98 route 97 36
99 TH conv 128 1 x 1 / 1 76 x 76 x 384 -> 76 x 76 x 128
100 TH conv 256 3 x 3 / 1 76 x 76 x 128 -> 76 x 76 x 256
101 TH conv 128 1 x 1 / 1 76 x 76 x 256 -> 76 x 76 x 128
102 TH conv 256 3 x 3 / 1 76 x 76 x 128 -> 76 x 76 x 256
103 TH conv 128 1 x 1 / 1 76 x 76 x 256 -> 76 x 76 x 128
104 TH conv 256 3 x 3 / 1 76 x 76 x 128 -> 76 x 76 x 256
105 TH conv 171 1 x 1 / 1 76 x 76 x 256 -> 76 x 76 x 171
106 detection
Loading weights from yolov3_gpu_4000.weights...
seen 64
Done!
video file: rtmp://192.168.110.48:1935/live/001
**Couldn't connect to webcam.
: Invalid argument**
如何解决此问题? 请帮助我获得有关RTMP上YOLO的经验。
答案 0 :(得分:0)
您能否检查网络摄像头连接/配置,因为网络摄像头连接错误,所以模型权重看起来已加载。