Alex_Lee
Alex_Lee
I am confused about the line 250 in lib/model/faster_rcnn/resnet.py why we should fix some layer in ResNet? # Fix blocks for p in self.RCNN_base[0].parameters(): p.requires_grad=False for p in self.RCNN_base[1].parameters(): p.requires_grad=False...
Some bugs caused by indent problem are fixed in this version!
The old version demo.py is not implemented for fpn specifically. The modified version is specifically updated for detecting objects by using fpn-trained model.