解决OSError: output/res101/voc_2007_trainval+voc_2012_trainval/default/res101_faster_rcnn_iter_110000.

解决OSError: output/res101/voc_2007_trainval+voc_2012_trainval/default/res101_faster_rcnn_iter_110000.ckpt.meta not found.

代码

tfmodel = os.path.join('/Users/.../.../tf-faster-rcnn/data/output', demonet, DATASETS[dataset][0], 'default',
                              NETS[demonet][0])


if not os.path.isfile(tfmodel + '.meta'):
        raise IOError(('{:s} not found.\nDid you download the proper networks from '
                       'our server and place them properly?').format(tfmodel + '.meta'))

报错信息

Traceback (most recent call last):
  File "demo.py", line 126, in <module>
    'our server and place them properly?').format(tfmodel + '.meta'))
OSError: output/res101/voc_2007_trainval+voc_2012_trainval/default/res101_faster_rcnn_iter_110000.ckpt.meta not found.
Did you download the proper networks from our server and place them properly?

解决办法

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-oUBuc30R-1608270568689)(evernotecid://A7BA1EDC-F70B-4A16-ABAA-EDD379BB023D/appyinxiangcom/29884553/ENResource/p211)]

自己手动创建和以上图片一致的目录,将res101_faster_rcnn_iter_110000.ckpt.meta模型文件放入

output/res101/voc_2007_trainval+voc_2012_trainval/default

软连接的做法，容易晕

欢迎大家交流学习，任何问题都可以留言

标签：res101,voc,default,trainval,meta,output
来源： https://blog.csdn.net/weixin_41194171/article/details/111357954