Python datasets.imdb() Examples

def selective_search_IJCV_roidb(self):
        """
        Return the database of selective search regions of interest.
        Ground-truth ROIs are also included.

        This function loads/saves from/to a cache file to speed up future calls.
        """
        cache_file = os.path.join(self.cache_path,
                '{:s}_selective_search_IJCV_top_{:d}_roidb.pkl'.
                format(self.name, self.config['top_k']))

        if os.path.exists(cache_file):
            with open(cache_file, 'rb') as fid:
                roidb = cPickle.load(fid)
            print '{} ss roidb loaded from {}'.format(self.name, cache_file)
            return roidb

        gt_roidb = self.gt_roidb()
        ss_roidb = self._load_selective_search_IJCV_roidb(gt_roidb)
        roidb = datasets.imdb.merge_roidbs(gt_roidb, ss_roidb)
        with open(cache_file, 'wb') as fid:
            cPickle.dump(roidb, fid, cPickle.HIGHEST_PROTOCOL)
        print 'wrote ss roidb to {}'.format(cache_file)

        return roidb 

def selective_search_IJCV_roidb(self):
        """
        Return the database of selective search regions of interest.
        Ground-truth ROIs are also included.

        This function loads/saves from/to a cache file to speed up future calls.
        """
        cache_file = os.path.join(self.cache_path,
                '{:s}_selective_search_IJCV_top_{:d}_roidb.pkl'.
                format(self.name, self.config['top_k']))

        if os.path.exists(cache_file):
            with open(cache_file, 'rb') as fid:
                roidb = cPickle.load(fid)
            print '{} ss roidb loaded from {}'.format(self.name, cache_file)
            return roidb

        gt_roidb = self.gt_roidb()
        ss_roidb = self._load_selective_search_IJCV_roidb(gt_roidb)
        roidb = datasets.imdb.merge_roidbs(gt_roidb, ss_roidb)
        with open(cache_file, 'wb') as fid:
            cPickle.dump(roidb, fid, cPickle.HIGHEST_PROTOCOL)
        print 'wrote ss roidb to {}'.format(cache_file)

        return roidb 

def selective_search_IJCV_roidb(self):
        """
        Return the database of selective search regions of interest.
        Ground-truth ROIs are also included.

        This function loads/saves from/to a cache file to speed up future calls.
        """
        cache_file = os.path.join(self.cache_path,
                '{:s}_selective_search_IJCV_top_{:d}_roidb.pkl'.
                format(self.name, self.config['top_k']))

        if os.path.exists(cache_file):
            with open(cache_file, 'rb') as fid:
                roidb = cPickle.load(fid)
            print '{} ss roidb loaded from {}'.format(self.name, cache_file)
            return roidb

        gt_roidb = self.gt_roidb()
        ss_roidb = self._load_selective_search_IJCV_roidb(gt_roidb)
        roidb = datasets.imdb.merge_roidbs(gt_roidb, ss_roidb)
        with open(cache_file, 'wb') as fid:
            cPickle.dump(roidb, fid, cPickle.HIGHEST_PROTOCOL)
        print 'wrote ss roidb to {}'.format(cache_file)

        return roidb 

def region_proposal_roidb(self):
        """
        Return the database of regions of interest.
        Ground-truth ROIs are also included.

        This function loads/saves from/to a cache file to speed up future calls.
        """
        cache_file = os.path.join(self.cache_path,
                                  self.name + '_' + cfg.SUBCLS_NAME + '_' + cfg.REGION_PROPOSAL + '_region_proposal_roidb.pkl')

        if os.path.exists(cache_file):
            with open(cache_file, 'rb') as fid:
                roidb = cPickle.load(fid)
            print '{} roidb loaded from {}'.format(self.name, cache_file)
            return roidb

        if self._image_set != 'testing':
            gt_roidb = self.gt_roidb()

            print 'Loading region proposal network boxes...'
            if self._image_set == 'trainval':
                model = cfg.REGION_PROPOSAL + '_trainval/'
            else:
                model = cfg.REGION_PROPOSAL + '_train/'
            rpn_roidb = self._load_rpn_roidb(gt_roidb, model)
            print 'Region proposal network boxes loaded'
            roidb = datasets.imdb.merge_roidbs(rpn_roidb, gt_roidb)
        else:
            print 'Loading region proposal network boxes...'
            model = cfg.REGION_PROPOSAL + '_trainval/'
            roidb = self._load_rpn_roidb(None, model)
            print 'Region proposal network boxes loaded'

        print '{} region proposals per image'.format(self._num_boxes_proposal / len(self.image_index))

        with open(cache_file, 'wb') as fid:
            cPickle.dump(roidb, fid, cPickle.HIGHEST_PROTOCOL)
        print 'wrote roidb to {}'.format(cache_file)

        return roidb 

def selective_search_roidb(self):
        """
        Return the database of selective search regions of interest.
        Ground-truth ROIs are also included.

        This function loads/saves from/to a cache file to speed up future calls.
        """
        cache_file = os.path.join(self.cache_path,
                                  self.name + '_selective_search_roidb.pkl')

        if os.path.exists(cache_file):
            with open(cache_file, 'rb') as fid:
                roidb = cPickle.load(fid)
            print '{} ss roidb loaded from {}'.format(self.name, cache_file)
            return roidb

        if int(self._year) == 2007 or self._image_set != 'test':
            gt_roidb = self.gt_roidb()
            ss_roidb = self._load_selective_search_roidb(gt_roidb)
            roidb = datasets.imdb.merge_roidbs(gt_roidb, ss_roidb)
        else:
            roidb = self._load_selective_search_roidb(None)
        with open(cache_file, 'wb') as fid:
            cPickle.dump(roidb, fid, cPickle.HIGHEST_PROTOCOL)
        print 'wrote ss roidb to {}'.format(cache_file)

        return roidb 

def region_proposal_roidb(self):
        """
        Return the database of regions of interest.
        Ground-truth ROIs are also included.

        This function loads/saves from/to a cache file to speed up future calls.
        """
        cache_file = os.path.join(self.cache_path,
                                  self.name + '_' + cfg.SUBCLS_NAME + '_' + cfg.REGION_PROPOSAL + '_region_proposal_roidb.pkl')

        if os.path.exists(cache_file):
            with open(cache_file, 'rb') as fid:
                roidb = cPickle.load(fid)
            print '{} roidb loaded from {}'.format(self.name, cache_file)
            return roidb

        if self._image_set != 'test':
            gt_roidb = self.gt_roidb()

            print 'Loading region proposal network boxes...'
            model = cfg.REGION_PROPOSAL
            rpn_roidb = self._load_rpn_roidb(gt_roidb, model)
            print 'Region proposal network boxes loaded'
            roidb = datasets.imdb.merge_roidbs(rpn_roidb, gt_roidb)
        else:
            print 'Loading region proposal network boxes...'
            model = cfg.REGION_PROPOSAL
            roidb = self._load_rpn_roidb(None, model)
            print 'Region proposal network boxes loaded'

        print '{} region proposals per image'.format(self._num_boxes_proposal / len(self.image_index))

        with open(cache_file, 'wb') as fid:
            cPickle.dump(roidb, fid, cPickle.HIGHEST_PROTOCOL)
        print 'wrote roidb to {}'.format(cache_file)

        return roidb 

def __init__(self, image_set, imagenet3d_path=None):
        datasets.imdb.__init__(self, 'imagenet3d_' + image_set)
        self._image_set = image_set
        self._imagenet3d_path = self._get_default_path() if imagenet3d_path is None \
                            else imagenet3d_path
        self._data_path = os.path.join(self._imagenet3d_path, 'Images')
        self._classes = ('__background__', 'aeroplane', 'ashtray', 'backpack', 'basket', \
             'bed', 'bench', 'bicycle', 'blackboard', 'boat', 'bookshelf', 'bottle', 'bucket', \
             'bus', 'cabinet', 'calculator', 'camera', 'can', 'cap', 'car', 'cellphone', 'chair', \
             'clock', 'coffee_maker', 'comb', 'computer', 'cup', 'desk_lamp', 'diningtable', \
             'dishwasher', 'door', 'eraser', 'eyeglasses', 'fan', 'faucet', 'filing_cabinet', \
             'fire_extinguisher', 'fish_tank', 'flashlight', 'fork', 'guitar', 'hair_dryer', \
             'hammer', 'headphone', 'helmet', 'iron', 'jar', 'kettle', 'key', 'keyboard', 'knife', \
             'laptop', 'lighter', 'mailbox', 'microphone', 'microwave', 'motorbike', 'mouse', \
             'paintbrush', 'pan', 'pen', 'pencil', 'piano', 'pillow', 'plate', 'pot', 'printer', \
             'racket', 'refrigerator', 'remote_control', 'rifle', 'road_pole', 'satellite_dish', \
             'scissors', 'screwdriver', 'shoe', 'shovel', 'sign', 'skate', 'skateboard', 'slipper', \
             'sofa', 'speaker', 'spoon', 'stapler', 'stove', 'suitcase', 'teapot', 'telephone', \
             'toaster', 'toilet', 'toothbrush', 'train', 'trash_bin', 'trophy', 'tub', 'tvmonitor', \
             'vending_machine', 'washing_machine', 'watch', 'wheelchair')
        self._class_to_ind = dict(zip(self.classes, xrange(self.num_classes)))
        self._image_ext = '.JPEG'
        self._image_index = self._load_image_set_index()
        # Default to roidb handler
        if cfg.IS_RPN:
            self._roidb_handler = self.gt_roidb
        else:
            self._roidb_handler = self.region_proposal_roidb

        self.config = {'top_k': 100000}

        # statistics for computing recall
        self._num_boxes_all = np.zeros(self.num_classes, dtype=np.int)
        self._num_boxes_covered = np.zeros(self.num_classes, dtype=np.int)
        self._num_boxes_proposal = 0

        assert os.path.exists(self._imagenet3d_path), \
                'imagenet3d path does not exist: {}'.format(self._imagenet3d_path)
        assert os.path.exists(self._data_path), \
                'Path does not exist: {}'.format(self._data_path) 

def selective_search_roidb(self):
        """
        Return the database of selective search regions of interest.
        Ground-truth ROIs are also included.

        This function loads/saves from/to a cache file to speed up future calls.
        """
        cache_file = os.path.join(self.cache_path,
                                  self.name + '_selective_search_roidb.pkl')

        if os.path.exists(cache_file):
            with open(cache_file, 'rb') as fid:
                roidb = pickle.load(fid)
            print ('{} ss roidb loaded from {}'.format(self.name, cache_file))
            return roidb

        if int(self._year) == 2007 or self._image_set != 'test':
            gt_roidb = self.gt_roidb()
            # ss_roidb = self._load_selective_search_roidb(gt_roidb)
            # roidb = datasets.imdb.merge_roidbs(gt_roidb, ss_roidb)
            roidb = self._load_selective_search_roidb(gt_roidb)
        elif int(self._year) == 2007 :
            gt_roidb = self.gt_roidb()
            roidb = self._load_selective_search_roidb(gt_roidb)		
        else:
            roidb = self._load_selective_search_roidb(None)
        with open(cache_file, 'wb') as fid:
            pickle.dump(roidb, fid, pickle.HIGHEST_PROTOCOL)
        print ('wrote ss roidb to {}'.format(cache_file))

        return roidb 

def __init__(self, image_set, year, devkit_path=None):
        datasets.imdb.__init__(self, 'voc_' + year + '_' + image_set)
        self._year = year
        self._image_set = image_set
        self._devkit_path = self._get_default_path() if devkit_path is None \
                            else devkit_path
        self._data_path = os.path.join(self._devkit_path, 'VOC' + self._year)
        self._classes = ('aeroplane', 'bicycle', 'bird', 'boat',
                         'bottle', 'bus', 'car', 'cat', 'chair',
                         'cow', 'diningtable', 'dog', 'horse',
                         'motorbike', 'person', 'pottedplant',
                         'sheep', 'sofa', 'train', 'tvmonitor')
        self._class_to_ind = dict(zip(self.classes, range(self.num_classes)))
        self._image_ext = '.jpg'
        self._image_index = self._load_image_set_index()
        # Default to roidb handler
        self._roidb_handler = self.selective_search_roidb
        self._salt = str(uuid.uuid4())
        self._comp_id = 'comp4'

        # PASCAL specific config options
        self.config = {'cleanup'  : True,
                       'use_salt' : True,
                       'use_diff' : False,
                       'matlab_eval' : False,
                       'top_k'    : 2000}

        assert os.path.exists(self._devkit_path), \
                'VOCdevkit path does not exist: {}'.format(self._devkit_path)
        assert os.path.exists(self._data_path), \
                'Path does not exist: {}'.format(self._data_path) 

def region_proposal_roidb(self):
        """
        Return the database of regions of interest.
        Ground-truth ROIs are also included.

        This function loads/saves from/to a cache file to speed up future calls.
        """
        cache_file = os.path.join(self.cache_path,
                                  self.name + '_' + cfg.SUBCLS_NAME + '_' + cfg.REGION_PROPOSAL + '_region_proposal_roidb.pkl')

        if os.path.exists(cache_file):
            with open(cache_file, 'rb') as fid:
                roidb = cPickle.load(fid)
            print '{} roidb loaded from {}'.format(self.name, cache_file)
            return roidb

        if self._image_set != 'testing':
            gt_roidb = self.gt_roidb()

            print 'Loading region proposal network boxes...'
            if self._image_set == 'trainval':
                model = cfg.REGION_PROPOSAL + '_trainval/'
            else:
                model = cfg.REGION_PROPOSAL + '_train/'
            rpn_roidb = self._load_rpn_roidb(gt_roidb, model)
            print 'Region proposal network boxes loaded'
            roidb = datasets.imdb.merge_roidbs(rpn_roidb, gt_roidb)
        else:
            print 'Loading region proposal network boxes...'
            model = cfg.REGION_PROPOSAL + '_trainval/'
            roidb = self._load_rpn_roidb(None, model)
            print 'Region proposal network boxes loaded'

        print '{} region proposals per image'.format(self._num_boxes_proposal / len(self.image_index))

        with open(cache_file, 'wb') as fid:
            cPickle.dump(roidb, fid, cPickle.HIGHEST_PROTOCOL)
        print 'wrote roidb to {}'.format(cache_file)

        return roidb 

def selective_search_roidb(self):
        """
        Return the database of selective search regions of interest.
        Ground-truth ROIs are also included.

        This function loads/saves from/to a cache file to speed up future calls.
        """
        cache_file = os.path.join(self.cache_path,
                                  self.name + '_selective_search_roidb.pkl')

        if os.path.exists(cache_file):
            with open(cache_file, 'rb') as fid:
                roidb = cPickle.load(fid)
            print '{} ss roidb loaded from {}'.format(self.name, cache_file)
            return roidb

        if int(self._year) == 2007 or self._image_set != 'test':
            gt_roidb = self.gt_roidb()
            ss_roidb = self._load_selective_search_roidb(gt_roidb)
            roidb = datasets.imdb.merge_roidbs(gt_roidb, ss_roidb)
        else:
            roidb = self._load_selective_search_roidb(None)
        with open(cache_file, 'wb') as fid:
            cPickle.dump(roidb, fid, cPickle.HIGHEST_PROTOCOL)
        print 'wrote ss roidb to {}'.format(cache_file)

        return roidb 

def selective_search_roidb(self):
        """
        Return the database of selective search regions of interest.
        Ground-truth ROIs are also included.

        This function loads/saves from/to a cache file to speed up future calls.
        """
        cache_file = os.path.join(self.cache_path,
                                  self.name + '_selective_search_roidb.pkl')

        if os.path.exists(cache_file):
            with open(cache_file, 'rb') as fid:
                roidb = cPickle.load(fid)
            print '{} ss roidb loaded from {}'.format(self.name, cache_file)
            return roidb

        if int(self._year) == 2007 or self._image_set != 'test':
            gt_roidb = self.gt_roidb()
            ss_roidb = self._load_selective_search_roidb(gt_roidb)
            roidb = datasets.imdb.merge_roidbs(gt_roidb, ss_roidb)
        else:
            roidb = self._load_selective_search_roidb(None)
        with open(cache_file, 'wb') as fid:
            cPickle.dump(roidb, fid, cPickle.HIGHEST_PROTOCOL)
        print 'wrote ss roidb to {}'.format(cache_file)

        return roidb 

def region_proposal_roidb(self):
        """
        Return the database of regions of interest.
        Ground-truth ROIs are also included.

        This function loads/saves from/to a cache file to speed up future calls.
        """
        cache_file = os.path.join(self.cache_path,
                                  self.name + '_' + cfg.REGION_PROPOSAL + '_region_proposal_roidb.pkl')

        if os.path.exists(cache_file):
            with open(cache_file, 'rb') as fid:
                roidb = cPickle.load(fid)
            print '{} roidb loaded from {}'.format(self.name, cache_file)
            return roidb

        if self._image_set != 'test':
            gt_roidb = self.gt_roidb()

            print 'Loading region proposal network boxes...'
            model = cfg.REGION_PROPOSAL
            rpn_roidb = self._load_rpn_roidb(gt_roidb, model)
            print 'Region proposal network boxes loaded'
            roidb = datasets.imdb.merge_roidbs(rpn_roidb, gt_roidb)
        else:
            print 'Loading region proposal network boxes...'
            model = cfg.REGION_PROPOSAL
            roidb = self._load_rpn_roidb(None, model)
            print 'Region proposal network boxes loaded'

        print '{} region proposals per image'.format(self._num_boxes_proposal / len(self.image_index))

        with open(cache_file, 'wb') as fid:
            cPickle.dump(roidb, fid, cPickle.HIGHEST_PROTOCOL)
        print 'wrote roidb to {}'.format(cache_file)

        return roidb 

def region_proposal_roidb(self):
        """
        Return the database of regions of interest.
        Ground-truth ROIs are also included.

        This function loads/saves from/to a cache file to speed up future calls.
        """
        cache_file = os.path.join(self.cache_path,
                                  self.name + '_' + cfg.SUBCLS_NAME + '_' + cfg.REGION_PROPOSAL + '_region_proposal_roidb.pkl')

        if os.path.exists(cache_file):
            with open(cache_file, 'rb') as fid:
                roidb = cPickle.load(fid)
            print '{} roidb loaded from {}'.format(self.name, cache_file)
            return roidb

        if self._image_set != 'test':
            gt_roidb = self.gt_roidb()

            print 'Loading region proposal network boxes...'
            model = 'train/'
            rpn_roidb = self._load_rpn_roidb(gt_roidb, model)
            print 'Region proposal network boxes loaded'
            roidb = datasets.imdb.merge_roidbs(rpn_roidb, gt_roidb)
        else:
            print 'Loading region proposal network boxes...'
            model = 'test/'
            roidb = self._load_rpn_roidb(None, model)
            print 'Region proposal network boxes loaded'

        print '{} region proposals per image'.format(self._num_boxes_proposal / len(self.image_index))

        with open(cache_file, 'wb') as fid:
            cPickle.dump(roidb, fid, cPickle.HIGHEST_PROTOCOL)
        print 'wrote roidb to {}'.format(cache_file)

        return roidb 

def __init__(self, image_set, year, devkit_path=None):
        datasets.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 = self._get_default_path() if devkit_path is None \
                            else devkit_path
        # 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._roidb_handler = self.gt_roidb

        self.competition_mode(False)

        self._data_name = image_set + year  # e.g., "val2014"

        if self._data_name == 'test-dev2015':
            self._data_name_path = 'test2015'
        else:
            self._data_name_path = self._data_name 

def __init__(self, image_set, year, devkit_path=None):
        datasets.imdb.__init__(self, 'voc_' + year + '_' + image_set)
        self._year = year
        self._image_set = image_set
        self._devkit_path = self._get_default_path() if devkit_path is None \
                            else devkit_path
        self._data_path = os.path.join(self._devkit_path, 'VOC' + self._year)
        self._classes = ('__background__', # always index 0
                         'aeroplane', 'bicycle', 'bird', 'boat',
                         'bottle', 'bus', 'car', 'cat', 'chair',
                         'cow', 'diningtable', 'dog', 'horse',
                         'motorbike', 'person', 'pottedplant',
                         'sheep', 'sofa', 'train', 'tvmonitor')

        self._class_to_ind = dict(zip(self.classes, xrange(self.num_classes)))
        self._image_ext = '.jpg'
        
        self._image_index = self._load_image_set_index()
        
        # Default to roidb handler
        self._roidb_handler = self.gt_roidb
        self._comp_id = 'comp4'
        # PASCAL specific config options
        self.config = {'cleanup'  : True,
                       'use_salt' : True}

        assert os.path.exists(self._devkit_path), \
                'VOCdevkit path does not exist: {}'.format(self._devkit_path)
        assert os.path.exists(self._data_path), \
                'Path does not exist: {}'.format(self._data_path) 

def region_proposal_roidb(self):
        """
        Return the database of regions of interest.
        Ground-truth ROIs are also included.

        This function loads/saves from/to a cache file to speed up future calls.
        """
        cache_file = os.path.join(self.cache_path,
                                  self.name + '_' + cfg.SUBCLS_NAME + '_' + cfg.REGION_PROPOSAL + '_region_proposal_roidb.pkl')

        if os.path.exists(cache_file):
            with open(cache_file, 'rb') as fid:
                roidb = cPickle.load(fid)
            print '{} roidb loaded from {}'.format(self.name, cache_file)
            return roidb

        if self._image_set != 'test':
            gt_roidb = self.gt_roidb()

            print 'Loading region proposal network boxes...'
            model = cfg.REGION_PROPOSAL
            rpn_roidb = self._load_rpn_roidb(gt_roidb, model)
            print 'Region proposal network boxes loaded'
            roidb = datasets.imdb.merge_roidbs(rpn_roidb, gt_roidb)
        else:
            print 'Loading region proposal network boxes...'
            model = cfg.REGION_PROPOSAL
            roidb = self._load_rpn_roidb(None, model)
            print 'Region proposal network boxes loaded'

        print '{} region proposals per image'.format(self._num_boxes_proposal / len(self.image_index))

        with open(cache_file, 'wb') as fid:
            cPickle.dump(roidb, fid, cPickle.HIGHEST_PROTOCOL)
        print 'wrote roidb to {}'.format(cache_file)

        return roidb 

def __init__(self, image_set, year, devkit_path=None):
        datasets.imdb.__init__(self, 'voc_' + year + '_' + image_set)
        self._year = year
        self._image_set = image_set
        self._devkit_path = self._get_default_path() if devkit_path is None \
                            else devkit_path
        self._data_path = os.path.join(self._devkit_path, 'VOC' + self._year)
        self._classes = ('aeroplane', 'bicycle', 'bird', 'boat',
                         'bottle', 'bus', 'car', 'cat', 'chair',
                         'cow', 'diningtable', 'dog', 'horse',
                         'motorbike', 'person', 'pottedplant',
                         'sheep', 'sofa', 'train', 'tvmonitor')
        self._class_to_ind = dict(zip(self.classes, xrange(self.num_classes)))
        self._image_ext = '.jpg'
        self._image_index = self._load_image_set_index()
        # Default to roidb handler
        self._roidb_handler = self.selective_search_roidb
        self._salt = str(uuid.uuid4())
        self._comp_id = 'comp4'

        # PASCAL specific config options
        self.config = {'cleanup'  : True,
                       'use_salt' : True,
                       'use_diff' : False,
                       'matlab_eval' : False,
                       'top_k'    : 2000}

        assert os.path.exists(self._devkit_path), \
                'VOCdevkit path does not exist: {}'.format(self._devkit_path)
        assert os.path.exists(self._data_path), \
                'Path does not exist: {}'.format(self._data_path) 

def selective_search_roidb(self):
        """
        Return the database of selective search regions of interest.
        Ground-truth ROIs are also included.

        This function loads/saves from/to a cache file to speed up future calls.
        """
        cache_file = os.path.join(self.cache_path,
                                  self.name + '_selective_search_roidb.pkl')

        if os.path.exists(cache_file):
            with open(cache_file, 'rb') as fid:
                roidb = cPickle.load(fid)
            print '{} ss roidb loaded from {}'.format(self.name, cache_file)
            return roidb

        if int(self._year) == 2007 or self._image_set != 'test':
            gt_roidb = self.gt_roidb()
            # ss_roidb = self._load_selective_search_roidb(gt_roidb)
            # roidb = datasets.imdb.merge_roidbs(gt_roidb, ss_roidb)
            roidb = self._load_selective_search_roidb(gt_roidb)
        else:
            roidb = self._load_selective_search_roidb(None)
        with open(cache_file, 'wb') as fid:
            cPickle.dump(roidb, fid, cPickle.HIGHEST_PROTOCOL)
        print 'wrote ss roidb to {}'.format(cache_file)

        return roidb 

def __init__(self, image_set, imagenet3d_path=None):
        datasets.imdb.__init__(self, 'imagenet3d_' + image_set)
        self._image_set = image_set
        self._imagenet3d_path = self._get_default_path() if imagenet3d_path is None \
                            else imagenet3d_path
        self._data_path = os.path.join(self._imagenet3d_path, 'Images')
        self._classes = ('__background__', 'aeroplane', 'ashtray', 'backpack', 'basket', \
             'bed', 'bench', 'bicycle', 'blackboard', 'boat', 'bookshelf', 'bottle', 'bucket', \
             'bus', 'cabinet', 'calculator', 'camera', 'can', 'cap', 'car', 'cellphone', 'chair', \
             'clock', 'coffee_maker', 'comb', 'computer', 'cup', 'desk_lamp', 'diningtable', \
             'dishwasher', 'door', 'eraser', 'eyeglasses', 'fan', 'faucet', 'filing_cabinet', \
             'fire_extinguisher', 'fish_tank', 'flashlight', 'fork', 'guitar', 'hair_dryer', \
             'hammer', 'headphone', 'helmet', 'iron', 'jar', 'kettle', 'key', 'keyboard', 'knife', \
             'laptop', 'lighter', 'mailbox', 'microphone', 'microwave', 'motorbike', 'mouse', \
             'paintbrush', 'pan', 'pen', 'pencil', 'piano', 'pillow', 'plate', 'pot', 'printer', \
             'racket', 'refrigerator', 'remote_control', 'rifle', 'road_pole', 'satellite_dish', \
             'scissors', 'screwdriver', 'shoe', 'shovel', 'sign', 'skate', 'skateboard', 'slipper', \
             'sofa', 'speaker', 'spoon', 'stapler', 'stove', 'suitcase', 'teapot', 'telephone', \
             'toaster', 'toilet', 'toothbrush', 'train', 'trash_bin', 'trophy', 'tub', 'tvmonitor', \
             'vending_machine', 'washing_machine', 'watch', 'wheelchair')
        self._class_to_ind = dict(zip(self.classes, xrange(self.num_classes)))
        self._image_ext = '.JPEG'
        self._image_index = self._load_image_set_index()
        # Default to roidb handler
        if cfg.IS_RPN:
            self._roidb_handler = self.gt_roidb
        else:
            self._roidb_handler = self.region_proposal_roidb

        self.config = {'top_k': 100000}

        # statistics for computing recall
        self._num_boxes_all = np.zeros(self.num_classes, dtype=np.int)
        self._num_boxes_covered = np.zeros(self.num_classes, dtype=np.int)
        self._num_boxes_proposal = 0

        assert os.path.exists(self._imagenet3d_path), \
                'imagenet3d path does not exist: {}'.format(self._imagenet3d_path)
        assert os.path.exists(self._data_path), \
                'Path does not exist: {}'.format(self._data_path) 

def selective_search_roidb(self):
        """
        Return the database of selective search regions of interest.
        Ground-truth ROIs are also included.

        This function loads/saves from/to a cache file to speed up future calls.
        """
        cache_file = os.path.join(self.cache_path,
                                  self.name + '_selective_search_roidb.pkl')

        if os.path.exists(cache_file):
            with open(cache_file, 'rb') as fid:
                roidb = cPickle.load(fid)
            print '{} ss roidb loaded from {}'.format(self.name, cache_file)
            return roidb

        if int(self._year) == 2007 or self._image_set != 'test':
            gt_roidb = self.gt_roidb()
            ss_roidb = self._load_selective_search_roidb(gt_roidb)
            roidb = datasets.imdb.merge_roidbs(gt_roidb, ss_roidb)
        else:
            roidb = self._load_selective_search_roidb(None)
        with open(cache_file, 'wb') as fid:
            cPickle.dump(roidb, fid, cPickle.HIGHEST_PROTOCOL)
        print 'wrote ss roidb to {}'.format(cache_file)

        return roidb 

def __init__(self, image_set, year, devkit_path=None):
        datasets.imdb.__init__(self, 'voc_' + year + '_' + image_set)
        self._year = year
        self._image_set = image_set
        self._devkit_path = self._get_default_path() if devkit_path is None \
                            else devkit_path
        self._data_path = os.path.join(self._devkit_path, 'VOC' + self._year)
        self._classes = ('aeroplane', 'bicycle', 'bird', 'boat',
                         'bottle', 'bus', 'car', 'cat', 'chair',
                         'cow', 'diningtable', 'dog', 'horse',
                         'motorbike', 'person', 'pottedplant',
                         'sheep', 'sofa', 'train', 'tvmonitor')
        self._class_to_ind = dict(zip(self.classes, xrange(self.num_classes)))
        self._image_ext = '.jpg'
        self._image_index = self._load_image_set_index()
        # Default to roidb handler
        self._roidb_handler = self.selective_search_roidb

        # PASCAL specific config options
        self.config = {'cleanup'  : True,
                       'use_salt' : True,
                       'use_diff' : False,
                       'top_k'    : 2000}

        assert os.path.exists(self._devkit_path), \
                'VOCdevkit path does not exist: {}'.format(self._devkit_path)
        assert os.path.exists(self._data_path), \
                'Path does not exist: {}'.format(self._data_path) 

def selective_search_roidb(self):
        """
        Return the database of selective search regions of interest.
        Ground-truth ROIs are also included.

        This function loads/saves from/to a cache file to speed up future calls.
        """
        cache_file = os.path.join(self.cache_path,
                                  self.name + '_selective_search_roidb.pkl')

        if os.path.exists(cache_file):
            with open(cache_file, 'rb') as fid:
                roidb = cPickle.load(fid)
            print '{} ss roidb loaded from {}'.format(self.name, cache_file)
            return roidb

        if int(self._year) == 2007 or self._image_set != 'test':
            gt_roidb = self.gt_roidb()
            # ss_roidb = self._load_selective_search_roidb(gt_roidb)
            # roidb = datasets.imdb.merge_roidbs(gt_roidb, ss_roidb)
            roidb = self._load_selective_search_roidb(gt_roidb)
        else:
            roidb = self._load_selective_search_roidb(None)
        with open(cache_file, 'wb') as fid:
            cPickle.dump(roidb, fid, cPickle.HIGHEST_PROTOCOL)
        print 'wrote ss roidb to {}'.format(cache_file)

        return roidb 

def __init__(self, image_set, year, pascal_path=None):
        datasets.imdb.__init__(self, 'voc_' + year + '_' + image_set)
        self._year = year
        self._image_set = image_set
        self._pascal_path = self._get_default_path() if pascal_path is None \
                            else pascal_path
        self._data_path = os.path.join(self._pascal_path, 'VOCdevkit' + self._year, 'VOC' + self._year)
        self._classes = ('__background__', # always index 0
                         'aeroplane', 'bicycle', 'bird', 'boat',
                         'bottle', 'bus', 'car', 'cat', 'chair',
                         'cow', 'diningtable', 'dog', 'horse',
                         'motorbike', 'person', 'pottedplant',
                         'sheep', 'sofa', 'train', 'tvmonitor')
        self._class_to_ind = dict(zip(self.classes, xrange(self.num_classes)))
        self._image_ext = '.jpg'
        self._image_index = self._load_image_set_index()
        # Default to roidb handler
        if cfg.IS_RPN:
            self._roidb_handler = self.gt_roidb
        else:
            self._roidb_handler = self.region_proposal_roidb

        # num of subclasses
        self._num_subclasses = 240 + 1

        # load the mapping for subcalss to class
        filename = os.path.join(self._pascal_path, 'subcategory_exemplars', 'mapping.txt')
        assert os.path.exists(filename), 'Path does not exist: {}'.format(filename)
        
        mapping = np.zeros(self._num_subclasses, dtype=np.int)
        with open(filename) as f:
            for line in f:
                words = line.split()
                subcls = int(words[0])
                mapping[subcls] = self._class_to_ind[words[1]]
        self._subclass_mapping = mapping

        # PASCAL specific config options
        self.config = {'cleanup'  : True,
                       'use_salt' : True,
                       'top_k'    : 2000}

        # statistics for computing recall
        self._num_boxes_all = np.zeros(self.num_classes, dtype=np.int)
        self._num_boxes_covered = np.zeros(self.num_classes, dtype=np.int)
        self._num_boxes_proposal = 0

        assert os.path.exists(self._pascal_path), \
                'PASCAL path does not exist: {}'.format(self._pascal_path)
        assert os.path.exists(self._data_path), \
                'Path does not exist: {}'.format(self._data_path) 

def __init__(self, image_set, nthu_path=None):
        datasets.imdb.__init__(self, 'nthu_' + image_set)
        self._image_set = image_set
        self._nthu_path = self._get_default_path() if nthu_path is None \
                            else nthu_path
        self._data_path = os.path.join(self._nthu_path, 'data')
        self._classes = ('__background__', 'Car', 'Pedestrian', 'Cyclist')
        self._class_to_ind = dict(zip(self.classes, xrange(self.num_classes)))
        self._image_ext = '.jpg'
        self._image_index = self._load_image_set_index()
        # Default to roidb handler
        if cfg.IS_RPN:
            self._roidb_handler = self.gt_roidb
        else:
            self._roidb_handler = self.region_proposal_roidb

        # num of subclasses
        self._num_subclasses = 227 + 36 + 36 + 1

        # load the mapping for subcalss to class
        filename = os.path.join(self._nthu_path, 'mapping.txt')
        assert os.path.exists(filename), 'Path does not exist: {}'.format(filename)
        
        mapping = np.zeros(self._num_subclasses, dtype=np.int)
        with open(filename) as f:
            for line in f:
                words = line.split()
                subcls = int(words[0])
                mapping[subcls] = self._class_to_ind[words[1]]
        self._subclass_mapping = mapping

        self.config = {'top_k': 100000}

        # statistics for computing recall
        self._num_boxes_all = np.zeros(self.num_classes, dtype=np.int)
        self._num_boxes_covered = np.zeros(self.num_classes, dtype=np.int)
        self._num_boxes_proposal = 0

        assert os.path.exists(self._nthu_path), \
                'NTHU path does not exist: {}'.format(self._nthu_path)
        assert os.path.exists(self._data_path), \
                'Path does not exist: {}'.format(self._data_path) 

def __init__(self, image_set, seq_name, kitti_tracking_path=None):
        datasets.imdb.__init__(self, 'kitti_tracking_' + image_set + '_' + seq_name)
        self._image_set = image_set
        self._seq_name = seq_name
        self._kitti_tracking_path = self._get_default_path() if kitti_tracking_path is None \
                            else kitti_tracking_path
        self._data_path = os.path.join(self._kitti_tracking_path, image_set, 'image_02')
        self._classes = ('__background__', 'Car', 'Pedestrian', 'Cyclist')
        self._class_to_ind = dict(zip(self.classes, xrange(self.num_classes)))
        self._image_ext = '.png'
        self._image_index = self._load_image_set_index()
        # Default to roidb handler
        if cfg.IS_RPN:
            self._roidb_handler = self.gt_roidb
        else:
            self._roidb_handler = self.region_proposal_roidb

        # num of subclasses
        if image_set == 'training' and seq_name != 'trainval':
            self._num_subclasses = 220 + 1
        else:
            self._num_subclasses = 472 + 1

        # load the mapping for subcalss to class
        if image_set == 'training' and seq_name != 'trainval':
            filename = os.path.join(self._kitti_tracking_path, 'voxel_exemplars', 'train', 'mapping.txt')
        else:
            filename = os.path.join(self._kitti_tracking_path, 'voxel_exemplars', 'trainval', 'mapping.txt')
        assert os.path.exists(filename), 'Path does not exist: {}'.format(filename)
        
        mapping = np.zeros(self._num_subclasses, dtype=np.int)
        with open(filename) as f:
            for line in f:
                words = line.split()
                subcls = int(words[0])
                mapping[subcls] = self._class_to_ind[words[1]]
        self._subclass_mapping = mapping

        self.config = {'top_k': 100000}

        # statistics for computing recall
        self._num_boxes_all = np.zeros(self.num_classes, dtype=np.int)
        self._num_boxes_covered = np.zeros(self.num_classes, dtype=np.int)
        self._num_boxes_proposal = 0

        assert os.path.exists(self._kitti_tracking_path), \
                'kitti_tracking path does not exist: {}'.format(self._kitti_tracking_path)
        assert os.path.exists(self._data_path), \
                'Path does not exist: {}'.format(self._data_path) 

def __init__(self, image_set, devkit_path, data_path):
        imdb.__init__(self, image_set)
        self._image_set = image_set
        self._devkit_path = devkit_path
        self._data_path = data_path
        synsets_image = sio.loadmat(os.path.join(self._devkit_path, 'data', 'meta_det.mat'))
        synsets_video = sio.loadmat(os.path.join(self._devkit_path, 'data', 'meta_vid.mat'))
        self._classes_image = ('__background__',)
        self._wnid_image = (0,)

        self._classes = ('__background__',)
        self._wnid = (0,)

        for i in xrange(200):
            self._classes_image = self._classes_image + (synsets_image['synsets'][0][i][2][0],)
            self._wnid_image = self._wnid_image + (synsets_image['synsets'][0][i][1][0],)

        for i in xrange(30):
            self._classes = self._classes + (synsets_video['synsets'][0][i][2][0],)
            self._wnid = self._wnid + (synsets_video['synsets'][0][i][1][0],)

        self._wnid_to_ind_image = dict(zip(self._wnid_image, xrange(201)))
        self._class_to_ind_image = dict(zip(self._classes_image, xrange(201)))

        self._wnid_to_ind = dict(zip(self._wnid, xrange(31)))
        self._class_to_ind = dict(zip(self._classes, xrange(31)))

        #check for valid intersection between video and image classes
        self._valid_image_flag = [0]*201

        for i in range(1,201):
            if self._wnid_image[i] in self._wnid_to_ind:
                self._valid_image_flag[i] = 1

        self._image_ext = ['.JPEG']

        self._image_index = self._load_image_set_index()
        # Default to roidb handler
        self._roidb_handler = self.gt_roidb

        # Specific config options
        self.config = {'cleanup'  : True,
                       'use_salt' : True,
                       'top_k'    : 2000}

        assert os.path.exists(self._devkit_path), 'Devkit path does not exist: {}'.format(self._devkit_path)
        assert os.path.exists(self._data_path), 'Path does not exist: {}'.format(self._data_path) 

def __init__(self, image_set, devkit_path, data_path):
        imdb.__init__(self, image_set)
        self._image_set = image_set
        self._devkit_path = devkit_path
        self._data_path = data_path
        synsets_image = sio.loadmat(os.path.join(self._devkit_path, 'data', 'meta_det.mat'))
        synsets_video = sio.loadmat(os.path.join(self._devkit_path, 'data', 'meta_vid.mat'))
        self._classes_image = ('__background__',)
        self._wnid_image = (0,)

        self._classes = ('__background__',)
        self._wnid = (0,)

        for i in xrange(200):
            self._classes_image = self._classes_image + (synsets_image['synsets'][0][i][2][0],)
            self._wnid_image = self._wnid_image + (synsets_image['synsets'][0][i][1][0],)

        for i in xrange(30):
            self._classes = self._classes + (synsets_video['synsets'][0][i][2][0],)
            self._wnid = self._wnid + (synsets_video['synsets'][0][i][1][0],)

        self._wnid_to_ind_image = dict(zip(self._wnid_image, xrange(201)))
        self._class_to_ind_image = dict(zip(self._classes_image, xrange(201)))

        self._wnid_to_ind = dict(zip(self._wnid, xrange(31)))
        self._class_to_ind = dict(zip(self._classes, xrange(31)))

        #check for valid intersection between video and image classes
        self._valid_image_flag = [0]*201

        for i in range(1,201):
            if self._wnid_image[i] in self._wnid_to_ind:
                self._valid_image_flag[i] = 1

        self._image_ext = ['.JPEG']

        self._image_index = self._load_image_set_index()
        # Default to roidb handler
        self._roidb_handler = self.gt_roidb

        # Specific config options
        self.config = {'cleanup'  : True,
                       'use_salt' : True,
                       'top_k'    : 2000}

        assert os.path.exists(self._devkit_path), 'Devkit path does not exist: {}'.format(self._devkit_path)
        assert os.path.exists(self._data_path), 'Path does not exist: {}'.format(self._data_path) 

def __init__(self, image_set, kitti_path=None):
        datasets.imdb.__init__(self, 'kitti_' + image_set)
        self._image_set = image_set
        self._kitti_path = self._get_default_path() if kitti_path is None \
                            else kitti_path
        self._data_path = os.path.join(self._kitti_path, 'data_object_image_2')
        self._classes = ('__background__', 'Car', 'Pedestrian', 'Cyclist')
        self._class_to_ind = dict(zip(self.classes, xrange(self.num_classes)))
        self._image_ext = '.png'
        self._image_index = self._load_image_set_index()
        # Default to roidb handler
        if cfg.IS_RPN:
            self._roidb_handler = self.gt_roidb
        else:
            self._roidb_handler = self.region_proposal_roidb

        # num of subclasses
        if image_set == 'train' or image_set == 'val':
            self._num_subclasses = 125 + 24 + 24 + 1
            prefix = 'validation'
        else:
            self._num_subclasses = 227 + 36 + 36 + 1
            prefix = 'test'

        # load the mapping for subcalss to class
        filename = os.path.join(self._kitti_path, cfg.SUBCLS_NAME, prefix, 'mapping.txt')
        assert os.path.exists(filename), 'Path does not exist: {}'.format(filename)
        
        mapping = np.zeros(self._num_subclasses, dtype=np.int)
        with open(filename) as f:
            for line in f:
                words = line.split()
                subcls = int(words[0])
                mapping[subcls] = self._class_to_ind[words[1]]
        self._subclass_mapping = mapping

        self.config = {'top_k': 100000}

        # statistics for computing recall
        self._num_boxes_all = np.zeros(self.num_classes, dtype=np.int)
        self._num_boxes_covered = np.zeros(self.num_classes, dtype=np.int)
        self._num_boxes_proposal = 0

        assert os.path.exists(self._kitti_path), \
                'KITTI path does not exist: {}'.format(self._kitti_path)
        assert os.path.exists(self._data_path), \
                'Path does not exist: {}'.format(self._data_path) 

def __init__(self, image_set, devkit_path, data_path):
        imdb.__init__(self, image_set)
        self._image_set = image_set
        self._devkit_path = devkit_path
        self._data_path = data_path
        synsets_image = sio.loadmat(os.path.join(self._devkit_path, 'data', 'meta_det.mat'))
        synsets_video = sio.loadmat(os.path.join(self._devkit_path, 'data', 'meta_vid.mat'))
        self._classes_image = ('__background__',)
        self._wnid_image = (0,)

        self._classes = ('__background__',)
        self._wnid = (0,)

        for i in xrange(200):
            self._classes_image = self._classes_image + (synsets_image['synsets'][0][i][2][0],)
            self._wnid_image = self._wnid_image + (synsets_image['synsets'][0][i][1][0],)

        for i in xrange(30):
            self._classes = self._classes + (synsets_video['synsets'][0][i][2][0],)
            self._wnid = self._wnid + (synsets_video['synsets'][0][i][1][0],)

        self._wnid_to_ind_image = dict(zip(self._wnid_image, xrange(201)))
        self._class_to_ind_image = dict(zip(self._classes_image, xrange(201)))

        self._wnid_to_ind = dict(zip(self._wnid, xrange(31)))
        self._class_to_ind = dict(zip(self._classes, xrange(31)))

        #check for valid intersection between video and image classes
        self._valid_image_flag = [0]*201

        for i in range(1,201):
            if self._wnid_image[i] in self._wnid_to_ind:
                self._valid_image_flag[i] = 1

        self._image_ext = ['.JPEG']

        self._image_index = self._load_image_set_index()
        # Default to roidb handler
        self._roidb_handler = self.gt_roidb

        # Specific config options
        self.config = {'cleanup'  : True,
                       'use_salt' : True,
                       'top_k'    : 2000}

        assert os.path.exists(self._devkit_path), 'Devkit path does not exist: {}'.format(self._devkit_path)
        assert os.path.exists(self._data_path), 'Path does not exist: {}'.format(self._data_path)