You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: doc/model/dpa2.md
+3-2Lines changed: 3 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -26,7 +26,7 @@ The descriptor follows two main stages:
26
26
27
27
1.**repinit (representation initializer)**
28
28
- Initializes and fuses type and geometry information from local environments.
29
-
2.**repformer (representation transformer)**
29
+
1.**repformer (representation transformer)**
30
30
- Stacked message-passing layers that update $\mathbf{f}$ and $\mathbf{g}$ channels through convolution/symmetrization/MLP and attention-style interactions.
31
31
32
32
The final descriptor is formed from learned single-atom representations and then passed to downstream fitting/model components.
@@ -36,7 +36,8 @@ The final descriptor is formed from learned single-atom representations and then
36
36
DPA-2 updates local features layer-by-layer with residual connections. Conceptually, each layer performs neighborhood aggregation using geometry-conditioned interactions:
0 commit comments