Halide Language for fast portable Computation on Images and Tensors
Seems like a good time to take another look at Halide. Their claims about building neural nets using Halide are fascinating. I guess we should ask why more people don't use it? I don't know, i'm just asking. The new differentiable Halide is also very interesting.
But let's get started at the beginning. What is Halide, and how does it work? Let's check it out.