About RealTime FCOS about adelaidet HOT 5 CLOSED

@lkevinzc these changing points are chosen by following https://arxiv.org/abs/1811.08883.

from adelaidet.

@tianzhi0549 Oh I see, "reduce the learning rate by 10× in the last 60k and last 20k iterations respectively, no matter how many total iterations"!

So I previously misunderstood the setting.

Thank you so much for pointing out!

from adelaidet.

@lkevinzc these changing points are chosen by following https://arxiv.org/abs/1811.08883.

Hi there~ Sorry for raising new questions under this old closed issue.

I am wondering why you chose sync_bn and bn for training the RT-FCOS? Will GN work better for smaller batch size?

Thanks!

from adelaidet.

@lkevinzc Using GN in the backbone needs to pre-train the backbone (with GN) on ImageNet again.

from adelaidet.

@lkevinzc Using GN in the backbone needs to pre-train the backbone (with GN) on ImageNet again.

Thank you so much for your prompt and helpful reply!

from adelaidet.