A better Dropout! Implementing DropBlock in PyTorch

DropBlock is available on glasses in my computer vision library! Today we are going to implement DropBlock in PyTorch! DropBlock introduced by Ghiasi et al is a regularization technique specifical crafter for images that empirically works better than Dropout. By why Dropout is not sufficient? Dropout is a regularization technique that randomly drops (set to zeros) parts of the input before passing it to the next layer.