Let us suppose we have an RGB image of 1024x720 and our Net inputs (and output mask) are of shape 512x512 with N classes.
So during training and inference, we need to convert our input image and mask to the desired shape of 512x512
But in real life scenario, when we are using it on Videos, images etc; we can't use the 512x512 image. Instead we need to use the original size. So how could we do this? How are we supposed to map / overlay / superimpose the predicted output mask of shape 512x512 to the input image of shape 1024x720 ?
Let us suppose we have an RGB image of
1024x720and ourNetinputs (and output mask) are of shape512x512withNclasses.So during training and inference, we need to convert our input image and mask to the desired shape of
512x512But in real life scenario, when we are using it on Videos, images etc; we can't use the
512x512image. Instead we need to use the original size. So how could we do this? How are we supposed to map / overlay / superimpose the predicted output mask of shape512x512to the input image of shape1024x720?