search

luuuyi / RefineDet.PyTorch

A higher performance PyTorch implementation of Single-Shot Refinement Neural Network for Object Detection
MIT License
235 stars 64 forks source link

python eval_refinedet.py 时出现一下问题不知道怎么回事请楼主给予解答 #22

Closed zhangqiang12345678 closed 5 years ago

zhangqiang12345678 commented 5 years ago

Evaluating detections Writing noise VOC results file Writing nova VOC results file VOC07 metric? Yes Traceback (most recent call last): File "eval_refinedet.py", line 444, in thresh=args.confidence_threshold) File "eval_refinedet.py", line 419, in test_net evaluate_detections(all_boxes, output_dir, dataset) File "eval_refinedet.py", line 424, in evaluate_detections do_python_eval(output_dir) File "eval_refinedet.py", line 177, in do_python_eval ovthresh=0.5, use_07_metric=use_07_metric) File "eval_refinedet.py", line 288, in voc_eval R = [obj for obj in recs[imagename] if obj['name'] == classname] KeyError: '0c8fbc9601a1fa4533e46b19bd276d80'

luuuyi commented 5 years ago

@zhangqiang12345678 从报错上来看是字典的key找不到，你可以在中间过程调试一下看看

zhangqiang12345678 commented 5 years ago

按照网上大家给出的思路，删掉了上一次训练遗留的cache，然后出现以下问题 obj_struct['pose'] = obj.find('pose').text

AttributeError: 'NoneType' object has no attribute 'text' 作者说根据xml来修改eval _refinedet.py中的语句。 博主能给点建议吗

luuuyi commented 5 years ago

@zhangqiang12345678 这是很基本的Python报错，跟算法没关系，你应该多调试一下。