support the DOS (electronic density of states) fitting#2449
Merged
Conversation
This reverts commit e3917fc.
add definition for make_compute_fparam & make_ttm_fparam
now we can use `compute temp` or `fix ttm` to update the fparam each MD step
now we can use `compute temp` or `fix ttm` to update the fparam each MD step
…. function name `make_compute_fparam` is changed to `make_fparam_from_compute`
support fitting electronic density of states (DOS)
add `dos` type
add example and basic doc to hands on the deepdos fitting
for more information, see https://pre-commit.ci
Codecov ReportPatch coverage:
Additional details and impacted files@@ Coverage Diff @@
## devel #2449 +/- ##
==========================================
- Coverage 75.19% 74.37% -0.83%
==========================================
Files 223 227 +4
Lines 22691 23378 +687
Branches 1673 1673
==========================================
+ Hits 17063 17387 +324
- Misses 4535 4895 +360
- Partials 1093 1096 +3
... and 3 files with indirect coverage changes Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here. ☔ View full report in Codecov by Sentry. |
Member
|
pre-commit.ci autofix |
for more information, see https://pre-commit.ci
wanghan-iapcm
requested changes
Apr 10, 2023
wanghan-iapcm
left a comment
wanghan-iapcm
left a comment
Collaborator
There was a problem hiding this comment.
- Please add UTs for your contributions. Thanks!
- The data in the example are for the demonstrative purposes. Currently they are too large (~600KB) to be included in the source code. Please reduce the size of the data.
njzjz
requested changes
Apr 10, 2023
Contributor
Author
|
thank you for the advice, i will revise the code. Also, i will add unit tests |
remove `ener_min` and `ener_max`, and improve some code
test inference of dos for single frame
for more information, see https://pre-commit.ci
check the output shape and value of `dos` and `atom_dos`
for more information, see https://pre-commit.ci
if atomic is True, the output of `dos` should be the sum of `atom_dos`
for more information, see https://pre-commit.ci
wanghan-iapcm
approved these changes
Apr 12, 2023
Member
Please note that only 27.76% of the new codes have been tested. |
fix output bug in \fit\dos.py, and add unit test for `DOSFitting`
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
njzjz
approved these changes
Apr 13, 2023
njzjz
left a comment
njzjz
left a comment
Member
There was a problem hiding this comment.
@wanghan-iapcm is it ok to merge? Indeed there are still some codes that are not covered.
Collaborator
sry i did not notice your comment. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
here i present the implementation of DeepDOS model [Phys. Rev. B 105, 174109 (2022)] in dpkit-devel branch
generally, i add a new
fitting_type = 'dos'to allow the DP to fit a vector. this vector can be global (dos.raw/npy) or atomic (atom_dos.raw/npy), whose length isnumb_dos.specifically,
fit/dos.py,loss/dos.py,model/dos.pyandinfer/deep_dos.pyis created to allow fitting and inference*/__init__.py,train/trainer.py,utils/argcheck.pyis updatedentrypoint/freeze.py,entrypoint/test.py, relevant functions are added to freeze and test the DeepDOS modeldoc/model/train-fitting-dos.mdexamples/dos/, the input script is provided in theexamples/dos/train/input.json, data sets are provided in theexamples/dos/data/