How to use datasets - 10 common examples

print('Using config:')
  pprint.pprint(cfg)

  # if has model, get the name from it
  # if does not, then just use the initialization weights
  if args.model:
    filename = os.path.splitext(os.path.basename(args.model))[0]
  else:
    filename = os.path.splitext(os.path.basename(args.weight))[0]

  tag = args.tag
  tag = tag if tag else 'default'
  filename = tag + '/' + filename

  imdb = get_imdb(args.imdb_name)
  imdb.competition_mode(args.comp_mode)

  tfconfig = tf.ConfigProto(allow_soft_placement=True)
  tfconfig.gpu_options.allow_growth=True

  # init session
  sess = tf.Session(config=tfconfig)
  # load network
  if args.net == 'vgg16':
    net = vgg16()
  elif args.net == 'res50':
    net = resnetv1(num_layers=50)
  elif args.net == 'res101':
    net = resnetv1(num_layers=101)
  elif args.net == 'res152':
    net = resnetv1(num_layers=152)

def __init__(self, image_set, year, devkit_path=None):
        imdb.__init__(self, 'voc_' + year + '_' + image_set)
        self._year = year
        self._image_set = image_set
        self._devkit_path = os.environ['HOME'] + '/data/Object_Detection/pascal/VOCdevkit'
        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.selective_search_roidb
        self._salt = str(uuid.uuid4())

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,
                       'rpn_file': None,
                       'min_size' : 2}
        # name, paths
        self._year = year
        self._image_set = image_set
        self._data_path = os.environ['HOME'] + '/data/Object_Detection/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_ind[cls])
                                         for cls in self._classes[1:]])

        for ix, obj in enumerate(objs):
            cls = coco_cat_id_to_class_ind[obj['category_id']]
            boxes[ix, :] = obj['clean_bbox']
            gt_classes[ix] = cls
            seg_areas[ix] = obj['area']
            if obj['iscrowd']:
                # Set overlap to -1 for all classes for crowd objects
                # so they will be excluded during training
                overlaps[ix, :] = -1.0
            else:
                overlaps[ix, cls] = 1.0

        ds_utils.validate_boxes(boxes, width=width, height=height)
        overlaps = scipy.sparse.csr_matrix(overlaps)
        return {'boxes' : boxes,
                'gt_classes': gt_classes,
                'gt_overlaps' : overlaps,
                'flipped' : False,
                'seg_areas' : seg_areas}

print 'Loading {} boxes'.format(method)
        for i, index in enumerate(self._image_index):
            if i % 1000 == 0:
                print '{:d} / {:d}'.format(i + 1, len(self._image_index))

            box_file = osp.join(
                cfg.DATA_DIR, 'coco_proposals', method, 'mat',
                self._get_box_file(index))

            raw_data = sio.loadmat(box_file)['boxes']
            boxes = np.maximum(raw_data - 1, 0).astype(np.uint16)
            if method == 'MCG':
                # Boxes from the MCG website are in (y1, x1, y2, x2) order
                boxes = boxes[:, (1, 0, 3, 2)]
            # Remove duplicate boxes and very small boxes and then take top k
            keep = ds_utils.unique_boxes(boxes)
            boxes = boxes[keep, :]
            keep = ds_utils.filter_small_boxes(boxes, self.config['min_size'])
            boxes = boxes[keep, :]
            boxes = boxes[:top_k, :]
            box_list.append(boxes)
            # Sanity check
            im_ann = self._COCO.loadImgs(index)[0]
            width = im_ann['width']
            height = im_ann['height']
            ds_utils.validate_boxes(boxes, width=width, height=height)
        return self.create_roidb_from_box_list(box_list, gt_roidb)

"""

  def get_roidb(imdb_name):
    imdb = get_imdb(imdb_name)
    print('Loaded dataset `{:s}` for training'.format(imdb.name))
    imdb.set_proposal_method(cfg.TRAIN.PROPOSAL_METHOD)
    print('Set proposal method: {:s}'.format(cfg.TRAIN.PROPOSAL_METHOD))
    roidb = get_training_roidb(imdb)
    return roidb

  roidbs = [get_roidb(s) for s in imdb_names.split('+')]
  roidb = roidbs[0]
  if len(roidbs) > 1:
    for r in roidbs[1:]:
      roidb.extend(r)
    tmp = get_imdb(imdb_names.split('+')[1])
    imdb = datasets.imdb.imdb(imdb_names, tmp.classes)
  else:
    imdb = get_imdb(imdb_names)
  return imdb, roidb

imdb = get_imdb(imdb_name)
    print('Loaded dataset `{:s}` for training'.format(imdb.name))
    imdb.set_proposal_method(cfg.TRAIN.PROPOSAL_METHOD)
    print('Set proposal method: {:s}'.format(cfg.TRAIN.PROPOSAL_METHOD))
    roidb = get_training_roidb(imdb)
    return roidb

  roidbs = [get_roidb(s) for s in imdb_names.split('+')]
  roidb = roidbs[0]
  if len(roidbs) > 1:
    for r in roidbs[1:]:
      roidb.extend(r)
    tmp = get_imdb(imdb_names.split('+')[1])
    imdb = datasets.imdb.imdb(imdb_names, tmp.classes)
  else:
    imdb = get_imdb(imdb_names)
  return imdb, roidb

def get_roidb(imdb_name):
        imdb = get_imdb(imdb_name)
        print('Loaded dataset `{:s}` for training'.format(imdb.name))
        imdb.set_proposal_method(cfg.TRAIN.PROPOSAL_METHOD)
        print('Set proposal method: {:s}'.format(cfg.TRAIN.PROPOSAL_METHOD))
        roidb = get_training_roidb(imdb)
        return roidb

    roidbs = [get_roidb(s) for s in imdb_names.split('+')]
    roidb = roidbs[0]

    if len(roidbs) > 1:
        for r in roidbs[1:]:
            roidb.extend(r)
        tmp = get_imdb(imdb_names.split('+')[1])
        imdb = datasets.imdb.imdb(imdb_names, tmp.classes)
    else:
        imdb = get_imdb(imdb_names)

    if training:
        roidb = filter_roidb(roidb)

    ratio_list, ratio_index = rank_roidb_ratio(roidb)

    return imdb, roidb, ratio_list, ratio_index

def combined_roidb(imdb_names):
    def get_roidb(imdb_name):
        imdb = get_imdb(imdb_name)
        print 'Loaded dataset `{:s}` for training'.format(imdb.name)
        imdb.set_proposal_method(cfg.TRAIN.PROPOSAL_METHOD)
        print 'Set proposal method: {:s}'.format(cfg.TRAIN.PROPOSAL_METHOD)
        roidb = get_training_roidb(imdb)
        return roidb

    roidbs = [get_roidb(s) for s in imdb_names.split('+')]
    roidb = roidbs[0]
    if len(roidbs) > 1:
        for r in roidbs[1:]:
            roidb.extend(r)
        imdb = datasets.imdb.imdb(imdb_names)
    else:
        imdb = get_imdb(imdb_names)
    return imdb, roidb

def __init__(self, version, image_set, ):
        imdb.__init__(self, 'vg_' + version + '_' + image_set)
        self._version = version
        self._image_set = image_set
        self._data_path = os.path.join(cfg.DATA_DIR, 'genome')
        self._img_path = os.path.join(cfg.DATA_DIR, 'vg')
        # VG specific config options
        self.config = {'cleanup' : False}

        # Load classes
        self._classes = ['__background__']
        self._class_to_ind = {}
        self._class_to_ind[self._classes[0]] = 0
        with open(os.path.join(self._data_path, self._version, 'objects_vocab.txt')) as f:
          count = 1
          for object in f.readlines():
            names = [n.lower().strip() for n in object.split(',')]
            self._classes.append(names[0])