Why reset_parameters? #4006
Answered
by
rusty1s
Jeriousman
asked this question in
Q&A
-
I see reset_parameters() in nn layers. It seems that it is 'a must' to do in GNN or PyG. Why should we use it? |
Beta Was this translation helpful? Give feedback.
Answered by
rusty1s
Feb 6, 2022
Replies: 1 comment 1 reply
-
It isn't a must. It's just a convenient method to reset the parameters of a model, e.g., for re-using the model across different model initializations. It also follows best-practice from PyTorch, see here. |
Beta Was this translation helpful? Give feedback.
1 reply
Answer selected by
Jeriousman
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
It isn't a must. It's just a convenient method to reset the parameters of a model, e.g., for re-using the model across different model initializations. It also follows best-practice from PyTorch, see here.