Low accuracy after linear evaluation
ryancampbell514 opened this issue · 2 comments
ryancampbell514 commented
Hello,
I ran main.py followed by linear.py using the default arguments. At the end of linear.py, my top-1 test accuracy was only able to reach 25%. Why is it that I do not achieve 92% top1 accuracy after the 100 epochs?
Thanks
leftthomas commented
@ryancampbell514 check your code, and use the arguments as paper said
YangYang commented
Do you achieve better performance on the linear evaluation stage? @ryancampbell514