coco.py 文件源码

def __init__(self, image_set, year):
        imdb.__init__(self, 'coco_' + year + '_' + image_set)
        # COCO specific config options
        self.config = {'top_k' : 2000,
                       'use_salt' : True,
                       'cleanup' : True,
                       'crowd_thresh' : 0.7,
                       'min_size' : 2}
        # name, paths
        self._year = year
        self._image_set = image_set
        self._data_path = osp.join(cfg.DATA_DIR, 'coco')
        # load COCO API, classes, class <-> id mappings
        self._COCO = COCO(self._get_ann_file())
        cats = self._COCO.loadCats(self._COCO.getCatIds())
        self._classes = tuple(['__background__'] + [c['name'] for c in cats])
        self._class_to_ind = dict(zip(self.classes, xrange(self.num_classes)))
        self._class_to_coco_cat_id = dict(zip([c['name'] for c in cats],
                                              self._COCO.getCatIds()))
        self._image_index = self._load_image_set_index()
        # Default to roidb handler
        self.set_proposal_method('selective_search')
        self.competition_mode(False)

        # Some image sets are "views" (i.e. subsets) into others.
        # For example, minival2014 is a random 5000 image subset of val2014.
        # This mapping tells us where the view's images and proposals come from.
        self._view_map = {
            'minival2014' : 'val2014',          # 5k val2014 subset
            'valminusminival2014' : 'val2014',  # val2014 \setminus minival2014
        }
        coco_name = image_set + year  # e.g., "val2014"
        self._data_name = (self._view_map[coco_name]
                           if self._view_map.has_key(coco_name)
                           else coco_name)
        # Dataset splits that have ground-truth annotations (test splits
        # do not have gt annotations)
        self._gt_splits = ('train', 'val', 'minival')