Error using run_ssd_live_demo.py

qfgaohao / pytorch-ssd

MobileNetV1, MobileNetV2, VGG based SSD/SSD-lite implementation in Pytorch 1.0 / Pytorch 0.4. Out-of-box support for retraining on Open Images dataset. ONNX and Caffe2 support. Experiment Ideas like CoordConv.

MIT License

1.39k stars 529 forks source link

Hi! Im trying to use this repo to re-train an ssd model. As the readme said, i tried to run : python3 run_ssd_live_demo.py mb1-ssd models/mobilenet-v1-ssd-mp-0_675.pth models/voc-model-labels.txt But i got this as output:

Inference time:  0.037155866622924805
Time: 0.04s, Detect Objects: 1.
Traceback (most recent call last):
  File "run_ssd_live_demo.py", line 76, in <module>
    cv2.rectangle(orig_image, (box[0], box[1]), (box[2], box[3]), (255, 255, 0), 4)
cv2.error: OpenCV(4.5.5) :-1: error: (-5:Bad argument) in function 'rectangle'
> Overload resolution failed:
>  - Can't parse 'pt1'. Sequence item with index 0 has a wrong type
>  - Can't parse 'pt1'. Sequence item with index 0 has a wrong type
>  - Can't parse 'rec'. Expected sequence length 4, got 2
>  - Can't parse 'rec'. Expected sequence length 4, got 2

I dont know what to do. Maybe the version of the OpenCV?

qfgaohao / pytorch-ssd

Error using run_ssd_live_demo.py #173