search

rbgirshick / py-faster-rcnn

Faster R-CNN (Python implementation) -- see https://github.com/ShaoqingRen/faster_rcnn for the official MATLAB version
Other
8.14k stars 4.11k forks source link

How to solve this problem? #336

Open khaledbay opened 8 years ago

khaledbay commented 8 years ago

Traceback (most recent call last): File "./tools/test_net.py", line 90, in test_net(net, imdb, max_per_image=args.max_per_image, vis=args.vis) File "/media/sage/3a621a44-a12e-4444-9bf4-bef717055250/py-faster-rcnn/tools/../lib/fast_rcnn/test.py", line 295, in test_net imdb.evaluate_detections(all_boxes, output_dir) File "/media/sage/3a621a44-a12e-4444-9bf4-bef717055250/py-faster-rcnn/tools/../lib/datasets/pascal_voc.py", line 322, in evaluate_detections self._do_python_eval(output_dir) File "/media/sage/3a621a44-a12e-4444-9bf4-bef717055250/py-faster-rcnn/tools/../lib/datasets/pascal_voc.py", line 285, in _do_python_eval use_07_metric=use_07_metric) File "/media/sage/3a621a44-a12e-4444-9bf4-bef717055250/py-faster-rcnn/tools/../lib/datasets/voc_eval.py", line 148, in voc_eval BB = BB[sorted_ind, :] IndexError: too many indices

sbrugman commented 8 years ago

I have the same problem on #338. Some files appear to be empty, producing this error.

ubenz55555 commented 7 years ago

check your xml file ，some class might not be included，better check it one by one

ubenz55555 commented 7 years ago

and also your trainset.txt、test.txt and train.txt ，check every item is included in these three files