Add pairwise tabulation as an independent model#3101
Add pairwise tabulation as an independent model#3101wanghan-iapcm merged 5 commits intodeepmodeling:develfrom
Conversation
Add pairwise tabulation as an independent model, which can be summed with DP (DP + PairTab) by the linear model, other than interpolation. PairTab can be used for any pairwise potentials, e.g., d3, LJ, ZBL, etc. Signed-off-by: Jinzhe Zeng <jinzhe.zeng@rutgers.edu>
Signed-off-by: Jinzhe Zeng <jinzhe.zeng@rutgers.edu>
Signed-off-by: Jinzhe Zeng <jinzhe.zeng@rutgers.edu>
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
| from deepmd.model.model import ( | ||
| Model, | ||
| ) |
Check notice
Code scanning / CodeQL
Cyclic import
| from deepmd.entrypoints.train import ( | ||
| update_one_sel, | ||
| ) |
Check notice
Code scanning / CodeQL
Cyclic import
Codecov ReportAttention:
Additional details and impacted files@@ Coverage Diff @@
## devel #3101 +/- ##
==========================================
+ Coverage 75.82% 75.86% +0.04%
==========================================
Files 246 247 +1
Lines 24995 25075 +80
Branches 1597 1597
==========================================
+ Hits 18952 19023 +71
- Misses 5105 5114 +9
Partials 938 938 ☔ View full report in Codecov by Sentry. |
Signed-off-by: Jinzhe Zeng <jinzhe.zeng@rutgers.edu>
Signed-off-by: Jinzhe Zeng <jinzhe.zeng@rutgers.edu>
| trainable=False, | ||
| initializer=tf.constant_initializer(tab_data, dtype=tf.float64), | ||
| ) | ||
| t_tmap = tf.constant(" ".join(self.type_map), name="tmap", dtype=tf.string) |
Check notice
Code scanning / CodeQL
Unused local variable
| initializer=tf.constant_initializer(tab_data, dtype=tf.float64), | ||
| ) | ||
| t_tmap = tf.constant(" ".join(self.type_map), name="tmap", dtype=tf.string) | ||
| t_mt = tf.constant(self.model_type, name="model_type", dtype=tf.string) |
Check notice
Code scanning / CodeQL
Unused local variable
| ) | ||
| t_tmap = tf.constant(" ".join(self.type_map), name="tmap", dtype=tf.string) | ||
| t_mt = tf.constant(self.model_type, name="model_type", dtype=tf.string) | ||
| t_ver = tf.constant(MODEL_VERSION, name="model_version", dtype=tf.string) |
Check notice
Code scanning / CodeQL
Unused local variable
| t_ver = tf.constant(MODEL_VERSION, name="model_version", dtype=tf.string) | ||
|
|
||
| with tf.variable_scope("fitting_attr" + suffix, reuse=reuse): | ||
| t_dfparam = tf.constant(0, name="dfparam", dtype=tf.int32) |
Check notice
Code scanning / CodeQL
Unused local variable
|
|
||
| with tf.variable_scope("fitting_attr" + suffix, reuse=reuse): | ||
| t_dfparam = tf.constant(0, name="dfparam", dtype=tf.int32) | ||
| t_daparam = tf.constant(0, name="daparam", dtype=tf.int32) |
Check notice
Code scanning / CodeQL
Unused local variable
| t_dfparam = tf.constant(0, name="dfparam", dtype=tf.int32) | ||
| t_daparam = tf.constant(0, name="daparam", dtype=tf.int32) | ||
| with tf.variable_scope("descrpt_attr" + suffix, reuse=reuse): | ||
| t_ntypes = tf.constant(self.ntypes, name="ntypes", dtype=tf.int32) |
Check notice
Code scanning / CodeQL
Unused local variable
| t_daparam = tf.constant(0, name="daparam", dtype=tf.int32) | ||
| with tf.variable_scope("descrpt_attr" + suffix, reuse=reuse): | ||
| t_ntypes = tf.constant(self.ntypes, name="ntypes", dtype=tf.int32) | ||
| t_rcut = tf.constant( |
Check notice
Code scanning / CodeQL
Unused local variable
2 participants
Add pairwise tabulation as an independent model, which can be summed with DP (DP + PairTab) by the linear model, other than interpolation. PairTab can be used for any pairwise potentials, e.g., d3, LJ, ZBL, etc.
Fix #3099.