Questions about evaluation on awa2

[CallMeNumber1]

Q1：If i want to evaluate on awa2，should i still train on imagenet？

[CallMeNumber1]

Q2：By the way, 24 out of 40 of the training classes in awa2 overlap with the ImageNet 2012 dataset. Does this mean that the rest of the training classes do not have corresponding ground truth classifier wights ?

[lil-wayne-0319]

yes, you can. cause awa2 is the subset of imageNet+22K

[lil-wayne-0319]

i think the ground truth weight of the unseen class is constructed by Resnet50 model and inputs from imageNet+22k, not your training set imageNet+1k