search

majumderb / rezero

Official PyTorch Repo for "ReZero is All You Need: Fast Convergence at Large Depth"
https://arxiv.org/pdf/2003.04887.pdf
MIT License
407 stars 52 forks source link

Can the method be applied to CNN? #1

Closed JunMa11 closed 4 years ago

calclavia commented 4 years ago

Yes it should work with any residual network. See section 6 in our paper.