Cheng JiKang comments

Results 4 comments of


                                            Cheng JiKang

It would be very kind that if you could provide the pre-trained model for CWAT and MTD.

Thank you so much for your reply. Not yet, and since we found some super abnormal phenomenon when training epoch is extremely large, we halted the research about this topic....

It would be very kind that if you could provide the pre-trained model for CWAT and MTD.

> Hi! Are you able to run the evaluation process with the pretrained RobustDet model they provided? Yes, the pretrained RobustDet model works well without any modification.

It would be very kind that if you could provide the pre-trained model for CWAT and MTD.

> > > Hi! Are you able to run the evaluation process with the pretrained RobustDet model they provided? > > > > > > Yes, the pretrained RobustDet model...

Unexpected results when training with multi-gpus

> The bug of multi-gpus training has been fixed in the latest version. You can update the code to the latest version. Thanks for your response. Training without CFR works...