Skip to content

“So we're able to essentially get rid of just our weight.…” — Practical AI at 12:49

Practical AI Large models on CPUs

“So we're able to essentially get rid of just our weight. Whenever I say get rid of, I mean, setting those parameters to zero within 95% of them. So you're left with 5% of your weights that are non-zero. That's actually all that you need to preserve the accuracy on ImageNet for ResNet 50, for example. And some quick…”

0:00 38:28