maudzung / SFA3D

Super Fast and Accurate 3D Object Detection based on 3D LiDAR Point Clouds (The PyTorch implementation)
https://github.com/maudzung/Super-Fast-Accurate-3D-Object-Detection
MIT License
1k stars 271 forks source link

corners_int is not int type #75

Closed ausk closed 1 year ago

ausk commented 1 year ago
raceback (most recent call last):  File "/home/cloudpoint/projs/SFA3D-master/sfa/test.py", line 152, in <module>
    bev_map = draw_predictions(bev_map, detections.copy(), configs.num_classes)
  File "/home/cloudpoint/projs/SFA3D-master/sfa/utils/evaluation_utils.py", line 162, in draw_predictions    drawRotatedBox(img, _x, _y, _w, _l, _yaw, cnf.colors[int(j)])
  File "/home/cloudpoint/projs/SFA3D-master/sfa/data_process/kitti_bev_utils.py", line 87, in drawRotatedBox    cv2.line(img, (corners_int[0, 0], corners_int[0, 1]), (corners_int[3, 0], corners_int[3, 1]), (255, 255, 0), 2)
cv2.error: OpenCV(4.6.0) :-1: error: (-5:Bad argument) in function 'line'
> 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
ausk commented 1 year ago

Fixed by: https://github.com/maudzung/SFA3D/pull/74