Custom Datasets have more than 255 category

[yuleung]

If my Custom Datasets have more than 255 category for Segmentation task，Can I use dataset APIs (DatasetCatalog, MetadataCatalog) add it for standard format？ How to do？

In Tutorials: https://detectron2.readthedocs.io/en/latest/tutorials/datasets.html#standard-dataset-dicts:

segmentation (list[list[float]] or dict): the segmentation mask of the instance.

If list[list[float]], it represents a list of polygons, one for each connected component of the object. Each list[float] is one simple polygon in the format of [x1, y1, ..., xn, yn] (n≥3). The Xs and Ys are absolute coordinates in unit of pixels.

If dict, it represents the per-pixel segmentation mask in COCO’s compressed RLE format. The dict should have keys “size” and “counts”. You can convert a uint8 segmentation mask of 0s and 1s into such dict by pycocotools.mask.encode(np.asarray(mask, order="F")). cfg.INPUT.MASK_FORMAT must be set to bitmask if using the default data loader with such format.

Just use ‘’list[list[float]]‘’? (segmentation (list[list[float]] or dict)