What does KeyError: u'area' means ?

Hi, everyone! When train my custom data using tutorial_2gpu_e2e_faster_rcnn_R-50-FPN, I met this error

INFO memonger.py: 97: Memonger memory optimization took 0.0219588279724 secs INFO train.py: 192: Loading dataset: ('voc_2007_train',) loading annotations into memory... Done (t=0.14s) creating index... index created! Traceback (most recent call last): File "tools/train_net.py", line 132, in main() File "tools/train_net.py", line 114, in main checkpoints = detectron.utils.train.train_model() File "/data2/xiangdawei/detectron/detectron/utils/train.py", line 58, in train_model setup_model_for_training(model, weights_file, output_dir) File "/data2/xiangdawei/detectron/detectron/utils/train.py", line 170, in setup_model_for_training add_model_training_inputs(model) File "/data2/xiangdawei/detectron/detectron/utils/train.py", line 194, in add_model_training_inputs cfg.TRAIN.DATASETS, cfg.TRAIN.PROPOSAL_FILES File "/data2/xiangdawei/detectron/detectron/datasets/roidb.py", line 61, in combined_roidb_for_training roidbs = [get_roidb(*args) for args in zip(dataset_names, proposal_files)] File "/data2/xiangdawei/detectron/detectron/datasets/roidb.py", line 46, in get_roidb crowd_filter_thresh=cfg.TRAIN.CROWD_FILTER_THRESH File "/data2/xiangdawei/detectron/detectron/datasets/json_dataset.py", line 109, in get_roidb self._add_gt_annotations(entry) File "/data2/xiangdawei/detectron/detectron/datasets/json_dataset.py", line 177, in _add_gt_annotations if obj['area'] < cfg.TRAIN.GT_MIN_AREA: KeyError: u'area'

Is this related to json file of the train annotations?