LoFTR
LoFTR copied to clipboard
why the result is different, when run the program every time.
Hi, I replase your 128 dimension feature map; in resnet_fpn.py 'x0 = self.relu(self.bn1(self.conv1(x)))'; i want to use my cnn net, but the result is different every time , sometimes matches 0 ,but sometimes matches 24.