Intel® Distribution of OpenVINO™ Toolkit
Community support and discussions about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all things computer vision-related on Intel® platforms.

An error in running the yolov3 demo

林__云泽
Beginner
208 Views
Hi! when I run the yolov3 demo ,it turns an error : root@UP2:~/inference_engine_samples_build/intel64/Release# ./object_detection_demo_yolov3_async -i cam -m /home/terasic/Desktop/FP32/frozen_darknet_yolov3_model.xml InferenceEngine: API version ............ 1.6 Build .................. custom_releases/2019/R1_c9b66a26e4d65bb986bb740e73f58c6e9e84c7c2 [ INFO ] Parsing input parameters [ INFO ] Reading input [ INFO ] Loading plugin API version ............ 1.6 Build .................. 22443 Description ....... MKLDNNPlugin [ INFO ] Loading network files [ ERROR ] Error reading network: in Layer detector/darknet-53/Conv_1/Conv2D: trying to connect an edge to non existing output port: 2.1
0 Kudos
2 Replies
林__云泽
Beginner
208 Views
  • this is the yolov3.json:

[
  {
    "id": "TFYOLOV3",
    "match_kind": "general",
    "custom_attributes": {
      "classes": 80,
      "coords": 4,
      "num": 9,
      "mask": [0, 1, 2],
      "entry_points": ["detector/yolo-v3/Reshape", "detector/yolo-v3/Reshape_4", "detector/yolo-v3/Reshape_8"]
    }
  }
]

Cary_P_Intel1
Employee
208 Views

Hi,

Which version of OpenVINO did you use? which pre-trained model did you use from darknet 416, 608 or tiny? Can you share the command you used to convert the darknet model to pb, also the pb file to IR?

Reply