0

I am doing semantic segmentation. Detectron2 can produce prediction mask labels as pictures.

Can I save the predicted annotation images in COCO file instead of pictures. The COCO file can be used for editing in annotation tools like labelme.

Do you have the Python script for extracting the predicted annotation images in COCO format.

Thanks.

Lim Cheng Wei
  • 11
  • 3
  • out = v.draw_instance_predictions(outputs["instances"].to("cpu")) cv2_imshow(out.get_image()[:, :, ::-1]) How can we save the out image in json file? – Lim Cheng Wei Feb 27 '23 at 07:32

0 Answers0