This is Pytorch re-implementation of our CVPR 2020 paper "Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation" (https://arxiv.org/abs/1911.10194)
After training the model on custom dataset, we want to visualize the predict result with trained weight. However, when use v.draw_panoptic_seg_predictions , the argument segments_info is not directly result from Panoptic-Deeplab prediction, the latter results contains three keys ['sem_seg', 'panoptic_seg', 'instances'], so we have no clue where the segements_info come from, is there any visulization tutorial we could follow?
After training the model on custom dataset, we want to visualize the predict result with trained weight. However, when use
v.draw_panoptic_seg_predictions
, the argumentsegments_info
is not directly result from Panoptic-Deeplab prediction, the latter results contains three keys ['sem_seg', 'panoptic_seg', 'instances'], so we have no clue where the segements_info come from, is there any visulization tutorial we could follow?