code_test/mmdet/core/mask/utils.py

# Copyright (c) OpenMMLab. All rights reserved.
import mmcv
import numpy as np
import pycocotools.mask as mask_util


def split_combined_polys(polys, poly_lens, polys_per_mask):
    """Split the combined 1-D polys into masks.

    A mask is represented as a list of polys, and a poly is represented as
    a 1-D array. In dataset, all masks are concatenated into a single 1-D
    tensor. Here we need to split the tensor into original representations.

    Args:
        polys (list): a list (length = image num) of 1-D tensors
        poly_lens (list): a list (length = image num) of poly length
        polys_per_mask (list): a list (length = image num) of poly number
            of each mask

    Returns:
        list: a list (length = image num) of list (length = mask num) of \
            list (length = poly num) of numpy array.
    """
    mask_polys_list = []
    for img_id in range(len(polys)):
        polys_single = polys[img_id]
        polys_lens_single = poly_lens[img_id].tolist()
        polys_per_mask_single = polys_per_mask[img_id].tolist()

        split_polys = mmcv.slice_list(polys_single, polys_lens_single)
        mask_polys = mmcv.slice_list(split_polys, polys_per_mask_single)
        mask_polys_list.append(mask_polys)
    return mask_polys_list


# TODO: move this function to more proper place
def encode_mask_results(mask_results):
    """Encode bitmap mask to RLE code.

    Args:
        mask_results (list | tuple[list]): bitmap mask results.
            In mask scoring rcnn, mask_results is a tuple of (segm_results,
            segm_cls_score).

    Returns:
        list | tuple: RLE encoded mask.
    """
    if isinstance(mask_results, tuple):  # mask scoring
        cls_segms, cls_mask_scores = mask_results
    else:
        cls_segms = mask_results
    num_classes = len(cls_segms)
    encoded_mask_results = [[] for _ in range(num_classes)]
    for i in range(len(cls_segms)):
        for cls_segm in cls_segms[i]:
            encoded_mask_results[i].append(
                mask_util.encode(
                    np.array(
                        cls_segm[:, :, np.newaxis], order='F',
                        dtype='uint8'))[0])  # encoded with RLE
    if isinstance(mask_results, tuple):
        return encoded_mask_results, cls_mask_scores
    else:
        return encoded_mask_results