How does DMPD deal with different local neighbour count? #670
mearcstapa-gqz
started this conversation in
General
Replies: 1 comment 6 replies
-
The size is set by users. |
Beta Was this translation helpful? Give feedback.
6 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Since the neural network need to take a fix-sized input, how does DMPD get the input to the MLP when the local neighbour count is different? The DMPD paper only mentioned that it uses sorted input data for an atom (such that it preserves symmetry), but for a different atom, the input length (neighbour count) could be different. Could you point me to the code where the model handles this?
Beta Was this translation helpful? Give feedback.
All reactions