stress format in training data #544
Closed
gly123456-phy
started this conversation in
General
Replies: 3 comments
-
|
It looks like it worked. |
Beta Was this translation helpful? Give feedback.
0 replies
-
|
The header should be in whatever format(s) ASE will recognize and correctly parse as the stress |
Beta Was this translation helpful? Give feedback.
0 replies
-
|
As a more general point, it is useful to use ase.io.read to parse DFT output files and ase.io.write to write the parsed information as xyz files wherever possible. ASE should support many DFT codes, so it's usually possible unless one is using a DFT code with file formats unknown to ASE. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Hello,
I am preparing training data containing stress. As I learned from the documentation, we should be careful about sign and the units of the stress. Nevertheless, I would like to ask what should we write on the header line of the .extxyz file. For example, is it OK that I have the header line as:
Lattice="7.995001309308119 0.0 0.0 0.0 7.995001309308119 0.0 0.0 0.0 8.313265000261556" Properties=species:S:1:pos:R:3:forces:R:3 stress="0.01264946 -0.00010375 0.00209891 -0.00010375 -0.00010375 0.01545443 0.00209891 0.01545443 -0.00210074" energy=-28627.283459223596 pbc="T T T"
Can this be recognized?
Thanks for your help in advance!
Beta Was this translation helpful? Give feedback.
All reactions