News for hackers. Stuff that matters.
Re:Accelerated PyTorch Training on M1 Mac by 6gvONxR4sf7o on Wednesday May 18, 2022 @12:25PM (#31424671)
> But why are people still reporting benchmark results on VGG?

It makes me feel like i’m missing something! Is is still used as a backbone in the same way as legacy code is everywhere, or is it something else entirely??

Re:Accelerated PyTorch Training on M1 Mac by sanxiyn on Wednesday May 18, 2022 @09:33PM (#31429682)
VGG works better for style transfer than ResNet (this is a surprising result, but empirically true), but that's the only case I am aware of.

https://arxiv.org/abs/2104.05623