train config used for segmentation on coco

yanxp / MetaR-CNN

Meta R-CNN : Towards General Solver for Instance-level Low-shot Learning

https://yanxp.github.io/metarcnn.html

177 stars 23 forks source link

Open YoungXIAO13 opened 4 years ago

YoungXIAO13 commented 4 years ago

Hi,

I'm trying to reproduce the results of few-shot segmentation on coco using your code and the Detectron.pytorch.

Could you tell me which configs are you using for training the Meta R-CNN (detection + segmentation) on coco?

li-yanling commented 3 years ago

Dear author,

I have a similar request, cause you provide MaskRCNN+ft your table 7. Would you mind providing your MaskRCNN config (e.g. FPN? resnet 50 or 101?