search

JJGO / hyperlight

Modular and intuitive Hypernetworks in Pytorch
Apache License 2.0
32 stars 3 forks source link

Residual connection #6

Open minhquoc0712 opened 1 year ago

minhquoc0712 commented 1 year ago

Hi, thank you for your interesting research.

I have a few questions regarding the code and paper:

  1. In the repository, I cannot find the code for the output residual connection of the hypernetwork, can you point it out?
  2. In the "Output Encoding" part of the paper, you introduce a set of learnable parameters. So will your training of hypernetwork + primary network will have a parameter count slightly larger than traditional training of primary network only?