Minami
Minami
 The program killed twice when I came to 84 epochs, do you have any idea about that? QAQ
 I set the setting all the same with yours, but there is only 46 mAP on ori,it is much less than mAP=56 in your paper. Is that normal?Or there...
I spent whole day try to use https://github.com/clovaai/WCT2 to transfer style, but I cannot change it to my own style.How you use it to transfer to your own style？
The author has not published the training code. There are only four style.How do you create 8types of domain?
There are only two style
Thank you very much for your answer, because I am a fresh man and lack of knowledge. Do you know if there is such a job which can use target...
 The code download imagenetpretrained res101 weights
Oh thanks, if I do not delete the pre-trained weights downloading in detectron2, will it cover the clip pre-trained init？
How can I use imagenet pre-train weights？ If I delete set_backbone_model then use imagenet pretrain, it can not work
Thank you！If I want to use RN50+FPN.yaml with RN50 clip init, maybe I should change "self.backbone.set_backbone_model(self.roi_heads.box_predictor.cls_score.visual_enc)"？