faster rcnn train test

./tools/test_net.py --gpu 0 --def /home/aigrp/kai/py-faster-rcnn/models/pascal_voc/VGG16/faster_rcnn_alt_opt/faster_rcnn_test.pt --net /home/aigrp/kai/py-faster-rcnn/output/faster_rcnn_alt_opt/voc_2007_trainval/VGG16_wood_final80000.caffemodel  --imdb voc_2007_test --cfg /home/aigrp/kai/py-faster-rcnn/experiments/cfgs/faster_rcnn_alt_opt.yml 

 

/home/aigrp/kai/py-faster-rcnn/tools/train_net.py --gpu 0 --imdb voc_2007_trainval --cfg /home/aigrp/kai/py-faster-rcnn/experiments/cfgs/faster_rcnn_end2end.yml --solver /home/aigrp/kai/py-faster-rcnn/models/pascal_voc/VGG16/faster_rcnn_end2end/solver.prototxt --iter 10000

 

cls = self._class_to_ind[obj.find('name').text.lower().strip()]
KeyError: 'char'

注意pascal_voc.py 里面类别名字修改。。

posted on 2017-12-26 13:29  klitech  阅读(189)  评论(0编辑  收藏  举报

导航