OpenLongTailRecognition-OLTR
OpenLongTailRecognition-OLTR copied to clipboard
Unable to reproduce baseline result on ImageNet-LT
Hi, I would like to ask for the plain model of Resnet10 on ImageNet_LT, how many epochs did you use? Because if I set it to 90 epochs the performance is much better than the reported baseline performance. Thank you!
I am also very curious about this issue. It seems to be better than stage2