Results 4 comments of Sangyun Lee

I think so. A24 is 7 after subtraction

We updated the links, they should be working now On Tue, May 23, 2023 at 12:39 PM Jing Chen ***@***.***> wrote: > me too > > — > Reply to...

I haven't thought about that, but my intuition is that it shouldn't matter so much because neural networks can learn such simple affine transformations in the first layer if needed.