ChuckGithub

ok,Thanks

I want to detect one category, what code needs to be changed?

好的,谢谢了,最近买了大神你写的那本书在学习,刚好用这个项目练练手,遇到问题还得向你多多请教

我想把RPN分离出来只做二分类的,但是执行到下面一句出了问题,能不能帮我分析一下,谢谢了 mean = t.Tensor(self.loc_normalize_mean).cuda().repeat(self.n_class)[None] std = t.Tensor(self.loc_normalize_std).cuda().repeat(self.n_class)[None] roi_cls_loc = (roi_cls_loc * std + mean) mean和std都是1x8的,roi_cls_loc是1x16650x4的

但是我把代码改成这样,这行代码`roi = roi.view(-1, 1, 4).expand_as(roi_cls_loc)`报的这样的错误RuntimeError: The expanded size of the tensor (8325) must match the existing size (300) at non-singleton dimension 0. ``` mean = t.Tensor(self.loc_normalize_mean).cuda().repeat(self.n_class-1)[None] std = t.Tensor(self.loc_normalize_std).cuda().repeat(self.n_class-1)[None] roi_cls_loc...

roi是300x4,roi_cls_loc是8325x2x4

好的,我再看看,谢谢了

Is this problem solved? @hepinghu @SystemErrorWang

I changed the pytorch version 0.4 it’s ok

sry