Can this implementation handle images without objects?
SingL3 opened this issue · comments
Hello!
I want to train a model with some samples that has no objects ( just background ).
Can this implementation handle that?
可以
@13070151771 意思是只要把 roidb = filter_for_training(roidb) 去掉就可以吗？
我看代码，大多数都对无目标图可以处理，但是有少部分似乎就无法处理，改完之后loss经常突然增大