Closed manli232111 closed 1 year ago
Hi, yes this should be possible by running the inference script with an additional --viz
argument. I'm not sure if it'll look sensible for the VIPSeg dataset though because the number of classes is quite high for it.
Thanks so much for your reply, I will try it
Hi Thanks for your excellent job! Did you provide visualization tool for Video Panoptic Segmentation on KITTI-STEP?