fighting_liu comments

Repositories
Issues
Comments

Results 4 comments of


                                            fighting_liu

AssertionError: assert len(top) == len(self._name_to_top_map)

Set cfg.TRAIN.HAS_RPN=False and try again!!!

FPN training: divide by zero, RPNL1Loss explodes

The same situation occurs to me when i use FPN+ResNet101+dcn to train my own dataset. But the same data works fine for ResNet101+dcn. Bad log looks like follows: Epoch[0] Batch...

Confused with your mAP computing!

@BobLiu20 I just use your val dataset 5k.

How to compute output volume of CONV1 and POOL1?

Thanks shicai!