训练自己yoloV3模型时出现“ValueError: Dimension 0 in both shapes must be equal, but are 1 and 18. Shapes are ”

情况描述:
win10  keras   pycharm下加载自己的.h5权重进行检测,结果出现

ValueError: Dimension 0 in both shapes must be equal, but are 1 and 18. Shapes are [1,1,1024,255] and [18,1024,1,1]. for 'Assign_360' (op: 'Assign') with input shapes: [1,1,1024,255], [18,1024,1,1].

 

解决办法:在yolo.py中,将classes_path  路径改为自己的类路径即可

训练自己yoloV3模型时出现“ValueError: Dimension 0 in both shapes must be equal, but are 1 and 18. Shapes are ”_第1张图片


--------------------- 
作者:LeslieNeverLie 
来源:CSDN 
原文:https://blog.csdn.net/weixin_38136156/article/details/86437715 
版权声明:本文为博主原创文章,转载请附上博文链接!

你可能感兴趣的:(程序报错,#,物体检测)