训练Faster RCNN出现的错误集合

问题（1）：

Appending horizontally-flipped training examples...
voc_2007_trainval gt roidb loaded from /home/xiebingbing/py-faster-rcnn/data/cache/voc_2007_trainval_gt_roidb.pkl
done
Preparing training data...
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 "/home/xiebingbing/py-faster-rcnn/tools/../lib/fast_rcnn/train.py", line 122, in get_training_roidb
    rdl_roidb.prepare_roidb(imdb)
  File "/home/xiebingbing/py-faster-rcnn/tools/../lib/roi_data_layer/roidb.py", line 27, in prepare_roidb
    roidb[i]['image'] = imdb.image_path_at(i)
IndexError: list index out of range

解决办法：删掉cache文件即可

问题2：

pb2.text_format.Merge(f.read(), self.solver_param) AttributeError: 'module' object has no attribute 'text_format' 

解决办法：pip install protobuf==2.6.0 

分析： 使用命令进行安装的时候，版本没有达到工程所需的，所以需要升级

参考：http://blog.csdn.net/allyli0022/article/details/70888933