hub / github.com/VincentHancoder/SSGD / preprocess_panoptic_gt

Function preprocess_panoptic_gt

mmdet/models/utils/panoptic_gt_processing.py:5–68 · view source on GitHub ↗

Preprocess the ground truth for a image. Args: gt_labels (Tensor): Ground truth labels of each bbox, with shape (num_gts, ). gt_masks (BitmapMasks): Ground truth masks of each instances of a image, shape (num_gts, h, w). gt_semantic_seg (Tensor |

(gt_labels, gt_masks, gt_semantic_seg, num_things,
                           num_stuff, img_metas)

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers

nothing calls this directly

Calls 3

catMethod · 0.80

to_tensorMethod · 0.45

padMethod · 0.45

Tested by

no test coverage detected