Created by: sukkyusun1

I changed my training data to voc format(xml) and trying to train ppyolo here are my configuration

TrainReader: inputs_def: fields: ['image', 'gt_bbox', 'gt_class', 'gt_score'] num_max_boxes: 200 dataset: !VOCDataSet #image_dir: train anno_path: trainval.txt dataset_dir: /home/sk/PaddleDetection/dataset/voc with_background: false use_default_label : false

EvalReader: inputs_def: fields: ['image', 'im_size', 'im_id'] num_max_boxes: 200 dataset: !VOCDataSet #image_dir: val anno_path: test.txt dataset_dir: /home/sk/PaddleDetection/dataset/voc with_background: false use_default_label : false result Traceback (most recent call last): File "/home/sk/PaddleDetection/tools/train.py", line 368, in main() File "/home/sk/PaddleDetection/tools/train.py", line 145, in main eval_reader = create_reader(cfg.EvalReader, devices_num=1) File "/home/sk/PaddleDetection/ppdet/data/reader.py", line 434, in create_reader reader = Reader(**cfg)() File "/home/sk/PaddleDetection/ppdet/data/reader.py", line 208, in init self._roidbs = self._dataset.get_roidb() File "/home/sk/PaddleDetection/ppdet/data/source/dataset.py", line 68, in get_roidb self.load_roidb_and_cname2cid() File "/home/sk/PaddleDetection/ppdet/data/source/voc.py", line 143, in load_roidb_and_cname2cid _difficult = int(obj.find('difficult').text) TypeError: int() argument must be a string, a bytes-like object or a number, not 'NoneType'

following error occured