Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models?
To appear at ICML 2023
Boris Knyazev, Doha Hwang, Simon Lacoste-Julien
https://arxiv.org/abs/2303.04143
See the list of pretrained GHN models here.
See code examples at github.com/SamsungSAILMontreal/ghn3