hizhangp / yolo_tensorflow

Tensorflow implementation of YOLO, including training and test phase.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

改变config文件中CELL_SIZE改变后程序出现错误

pengzi2017 opened this issue · comments

我将config文件中的CELL_SIZE由7变成14后,运行程序出现了错误,显示是pascal_voc.py文件第44行两个矩阵赋值时现状不一致。
labels[count, :, :, :] = self.gt_labels[self.cursor]['label'] ValueError: could not broadcast input array from shape (7,7,7) into shape (14,14,7)
我自己检查了检查了很久,梳理了其中的逻辑关系,但就是找不出bug在哪儿。

程序中将CELL_SIZE由7变为14后,根本就没有任何关于7的定义或别的内容,定义的现状也是(14,14,5+len(classes)),但是程序运行后就会出现(7,7,5+len(classes))的现状,感觉很诡异。

I think the output cell size is decided by the size of input image and the stride of network,not only the cell size in config. py.