mask_adapter/data/datasets/register_coco_stuff_164k.py

"""
This file may have been modified by Bytedance Ltd. and/or its affiliates (“Bytedance's Modifications”).
All Bytedance's Modifications are Copyright (year) Bytedance Ltd. and/or its affiliates. 

Reference: https://github.com/MendelXu/SAN/blob/main/san/data/datasets/register_coco_stuff_164k.py
"""

import os

from detectron2.data import DatasetCatalog, MetadataCatalog
from detectron2.data.datasets import load_sem_seg

from . import openseg_classes

COCO_CATEGORIES = openseg_classes.get_coco_stuff_categories_with_prompt_eng()


def _get_coco_stuff_meta():
    # Id 0 is reserved for ignore_label, we change ignore_label for 0
    # to 255 in our pre-processing.
    stuff_ids = [k["id"] for k in COCO_CATEGORIES]
    assert len(stuff_ids) == 171, len(stuff_ids)

    # For semantic segmentation, this mapping maps from contiguous stuff id
    # (in [0, 91], used in models) to ids in the dataset (used for processing results)
    stuff_dataset_id_to_contiguous_id = {k: i for i, k in enumerate(stuff_ids)}
    stuff_classes = [k["name"] for k in COCO_CATEGORIES]

    ret = {
        "stuff_dataset_id_to_contiguous_id": stuff_dataset_id_to_contiguous_id,
        "stuff_classes": stuff_classes,
    }
    return ret


def register_all_coco_stuff_164k(root):
    root = os.path.join(root, "coco")
    meta = _get_coco_stuff_meta()

    for name, image_dirname, sem_seg_dirname in [
        ("train", "train2017", "stuffthingmaps_detectron2/train2017"),
        ("test", "val2017", "stuffthingmaps_detectron2/val2017"),
    ]:
        image_dir = os.path.join(root, image_dirname)
        gt_dir = os.path.join(root, sem_seg_dirname)
        all_name = f"openvocab_coco_2017_{name}_stuff_sem_seg"
        DatasetCatalog.register(
            all_name,
            lambda x=image_dir, y=gt_dir: load_sem_seg(
                y, x, gt_ext="png", image_ext="jpg"
            ),
        )
        MetadataCatalog.get(all_name).set(
            image_root=image_dir,
            sem_seg_root=gt_dir,
            evaluator_type="sem_seg",
            ignore_label=255,
            **meta,
        )


_root = os.getenv("DETECTRON2_DATASETS", "datasets")
register_all_coco_stuff_164k(_root)