Faster R-CNN训练问题解决：py-faster-rcnn/lib/datasets/imdb.py问题

最新推荐文章于 2025-04-01 09:47:31 发布

cv.exp

最新推荐文章于 2025-04-01 09:47:31 发布

阅读量869

点赞数

分类专栏： Deep Learning

本文链接：https://blog.youkuaiyun.com/forest_world/article/details/78069096

版权

Deep Learning 专栏收录该内容

172 篇文章

订阅专栏

本文记录了使用Faster R-CNN进行目标检测训练过程中遇到的一个具体错误：IndexError:index9isoutofboundsforaxis1withsize2。通过分析代码堆栈，发现该错误发生在处理翻转图像的边界框时，对错误原因进行了探讨，并提供了可能的解决方案。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

Loaded dataset `voc_2007_trainval` for training
Set proposal method: rpn
Appending horizontally-flipped training examples...
voc_2007_trainval gt roidb loaded from /home/py-faster-rcnn/data/cache/voc_2007_trainval_gt_roidb.pkl
loading /home/py-faster-rcnn/output/faster_rcnn_alt_opt/voc_2007_trainval/zf_rpn_stage1_iter_80000_proposals.pkl
Process Process-3:
Traceback (most recent call last):
  File "/usr/lib/python2.7/multiprocessing/process.py", line 258, in _bootstrap
    self.run()
  File "/usr/lib/python2.7/multiprocessing/process.py", line 114, in run
    self._target(*self._args, **self._kwargs)
  File "./tools/train_faster_rcnn_alt_opt.py", line 189, in train_fast_rcnn
    roidb, imdb = get_roidb(imdb_name, rpn_file=rpn_file)
  File "./tools/train_faster_rcnn_alt_opt.py", line 67, in get_roidb
    roidb = get_training_roidb(imdb)
  File "/home/py-faster-rcnn/tools/../lib/fast_rcnn/train.py", line 118, in get_training_roidb
    imdb.append_flipped_images()
  File "/home/py-faster-rcnn/tools/../lib/datasets/imdb.py", line 107, in append_flipped_images
    boxes = self.roidb[i]['boxes'].copy()
  File "/home/py-faster-rcnn/tools/../lib/datasets/imdb.py", line 67, in roidb
    self._roidb = self.roidb_handler()
  File "/home/py-faster-rcnn/tools/../lib/datasets/pascal_voc.py", line 141, in rpn_roidb
    rpn_roidb = self._load_rpn_roidb(gt_roidb)
  File "/home/py-faster-rcnn/tools/../lib/datasets/pascal_voc.py", line 155, in _load_rpn_roidb
    return self.create_roidb_from_box_list(box_list, gt_roidb)
  File "/home/py-faster-rcnn/tools/../lib/datasets/imdb.py", line 227, in create_roidb_from_box_list
    overlaps[I, gt_classes[argmaxes[I]]] = maxes[I]
IndexError: index 9 is out of bounds for axis 1 with size 2