endernewton / tf-faster-rcnn

Tensorflow Faster RCNN for Object Detection
https://arxiv.org/pdf/1702.02138.pdf
MIT License
3.65k stars 1.57k forks source link

There is a problem in the test link after the training. It should be what the previous test file saved. After the data and test file are replaced, an error is reported. #422

Open huaxv opened 5 years ago

huaxv commented 5 years ago

Writing person VOC results file Writing motorbike VOC results file VOC07 metric? Yes Traceback (most recent call last): File "./tools/test_net.py", line 120, in test_net(sess, net, imdb, filename, max_per_image=args.max_per_image) File "/home/amax/yang4/zgaibug/tf-faster-rcnn/tools/../lib/model/test.py", line 192, in test_net imdb.evaluate_detections(all_boxes, output_dir) File "/home/amax/yang4/zgaibug/tf-faster-rcnn/tools/../lib/datasets/pascal_voc.py", line 279, in evaluate_detections self._do_python_eval(output_dir) File "/home/amax/yang4/zgaibug/tf-faster-rcnn/tools/../lib/datasets/pascal_voc.py", line 242, in _do_python_eval use_07_metric=use_07_metric, use_diff=self.config['use_diff']) File "/home/amax/yang4/zgaibug/tf-faster-rcnn/tools/../lib/datasets/voc_eval.py", line 135, in voc_eval R = [obj for obj in recs[imagename] if obj['name'] == classname] KeyError: '000006' Command exited with non-zero status 1 2539.85user 176.37system 3:04.95elapsed 1468%CPU (0avgtext+0avgdata 2184836maxresident)k 0inputs+10608outputs (0major+1000596minor)pagefaults 0swaps

shirleyatgithub commented 3 years ago

Hi, huaxv, I have encountered the same error as yours. Have you solved this problem? could you tell me how to?