jessemelpolio / Faster_RCNN_for_DOTA

Code used for training Faster R-CNN on DOTA
https://arxiv.org/abs/1711.10398
Apache License 2.0
336 stars 102 forks source link

RESUME:false in yaml file #34

Closed FoilHao closed 5 years ago

FoilHao commented 5 years ago

I notice that after the train ceased, I can't resume training based on my half-tained model. Is it because the parameter RESUME is set false in the DOTA_quadrangle.yaml file? If I set it true , will it automatically resume training based on the params and states file I got in the last training?

jessemelpolio commented 5 years ago

Yes, it will.

FoilHao commented 5 years ago

Thank you so much. You can close this issue.