ubuntu下py-faster rcnn训练单类数据库报错了,求跑过的大兄弟帮忙看下,不甚感谢。

参照别人博客我改过如下地方:pascal_voc.py中将类别数改为单类了
self._classes = ('__background__', # always index 0
'person')
/models/pascal_voc/ZF/faster_rcnn_alt_opt/*train(test).pt目录下
num_classes 21 → 2
bbox_num 84 → 8
训练时后面报了如下错误:
Process Process-1:
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 122, in train_rpn
    roidb, imdb = get_roidb(imdb_name)
  File "./tools/train_faster_rcnn_alt_opt.py", line 67, in get_roidb
    roidb = get_training_roidb(imdb)
  File "/media/dl/c0d34b51-8a78-4364-bc19-35003bf01885/RCNN/py-faster-rcnn/tools/../lib/fast_rcnn/train.py", line 118, in get_training_roidb
    imdb.append_flipped_images()
  File "/media/dl/c0d34b51-8a78-4364-bc19-35003bf01885/RCNN/py-faster-rcnn/tools/../lib/datasets/imdb.py", line 107, in append_flipped_images
    boxes = self.roidb[i]['boxes'].copy()
  File "/media/dl/c0d34b51-8a78-4364-bc19-35003bf01885/RCNN/py-faster-rcnn/tools/../lib/datasets/imdb.py", line 67, in roidb
    self._roidb = self.roidb_handler()
  File "/media/dl/c0d34b51-8a78-4364-bc19-35003bf01885/RCNN/py-faster-rcnn/tools/../lib/datasets/pascal_voc.py", line 103, in gt_roidb
    for index in self.image_index]
  File "/media/dl/c0d34b51-8a78-4364-bc19-35003bf01885/RCNN/py-faster-rcnn/tools/../lib/datasets/pascal_voc.py", line 204, in _load_pascal_annotation
    x1 = float(bbox.find('xmin').text) - 1
ValueError: invalid literal for float(): 737,
 
已邀请:

王斌_ICT - 研究领域:深度学习,目标检测

赞同来自: moyan

检查一下标记数据,写一个测试程序将标记文件每个目标的坐标值检测一下,是不是有负数或者大于当前图像的长宽的值.

qingtongli - 小菜鸟

赞同来自:

你好,请问faster rcnn 可以用cpu训练吗?

要回复问题请先登录注册