Detectron.pytorch
Detectron.pytorch copied to clipboard
How is the segmentation evaluated in mask rcnn?
Can anyone tell as to what metric is used for evaluating the Segmentation masks in Mask-RCNN and how is it implemented, because in the code, I can see that its using the same metric as the bounding box detection. How can the Dice Coefficient, used in this kaggle challenge be used here?
you can follow the cocoapi