vugia truong

@gnscc Well it is very odd. Because this C++ inference speed is even slower than python without converting into tensorRT. I guess some python magics does put those post-processing in...

Me too. Same problem

@SteveMacenski @mintar I think we could use the design of PasCalVOC dataset for this problem. For example, this is JPEGImage :  The mask for class segmentation (semantic segmentation) is...

@SteveMacenski Maybe my writting is a little bit confused. For sementic segmentation, 1 mask image is needed: 1 mask image for class as showed in 2nd picture. For instance segmentation...