XiangqianMa
XiangqianMa
I think you can not train your data with the author's weight, because this weight is suit for this special net which classes number is 20.
It's because of the version of tensorflow, 1.* rather than 0.* . @lei9wang
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.
My model can get the loss of 3, but it can not detect any right objects. Before i trained this model to fine-tune my own data, i have tried to...