Approximation of the memory usage

[fansgit]

"We benchmark all models with a minibatch size of 16 and an image size of 224 x 224; this allows direct comparisons between models, and allows all but the ResNet-200 model to run on the GTX 1080, which has only 8GB of memory."

I'm curious about arithmetic approximation of the memory usage on a given model if there is one.