How can the FCN responsible for predicting masks deal with the different dimensions of the ROI?
it seems the output of masking ROI is 1414number of classes
How can I actually reconstruct the mask based on 14*14 info and in reality the mask visualized might
be larger?
Thanks
Hello,
How can the FCN responsible for predicting masks deal with the different dimensions of the ROI? it seems the output of masking ROI is 1414number of classes How can I actually reconstruct the mask based on 14*14 info and in reality the mask visualized might be larger? Thanks