noUmbrella
noUmbrella
So, now, we can use the torch.nn.LocalResponseNorm instead of your own LRN?
Hi, I find that this code has a serious bug in rfcn.py at 212 and 213, I think it should be self.rfcn_bbox = Conv2d(1024,7*7*8, 1,1, bn=False) self.rfcn_score = Conv2d(1024, 7*7*self.n_classes,1,1,bn=False),...
Hi, I find that this code has a serious bug in rfcn.py at 212 and 213, I think it should be self.rfcn_bbox = Conv2d(1024,778, 1,1, bn=False) self.rfcn_score = Conv2d(1024, 77self.n_classes,1,1,bn=False),...
I test the mAP is very small, about 0.25. I found that, the classify is right and the regression is not work@RichardMrLu
Hi, do you find the bug? Does the Position Pooling Layer exists problem? @Rizhiy
Hi, do you find the bug? Does the Position Pooling Layer exists problem? @RichardMrLu