feat: atom_ener in energy fitting

deepmd/dpmodel/fitting/general_fitting.py

@@ -73,7 +73,10 @@
             different fitting nets for different atom types.
     exclude_types: List[int]
             Atomic contributions of the excluded atom types are set zero.
-
+    remove_vaccum_contribution: List[bool], optional
+        Remove vaccum contribution before the bias is added. The list assigned each
+        type. If not mixed_types, only remove the vaccum contribution for the atom types
+        in the list.
     """
 
     def __init__(
@@ -95,6 +98,7 @@
         spin: Any = None,
         mixed_types: bool = True,
         exclude_types: List[int] = [],
+        remove_vaccum_contribution: Optional[List[bool]] = None,
     ):
         self.var_name = var_name
         self.ntypes = ntypes
@@ -119,6 +123,7 @@
         self.exclude_types = exclude_types
         if self.spin is not None:
             raise NotImplementedError("spin is not supported")
+        self.remove_vaccum_contribution = remove_vaccum_contribution
 
         self.emask = AtomExcludeMask(self.ntypes, self.exclude_types)
 
@@ -298,6 +303,14 @@
                 "which is not consistent with {self.dim_descrpt}."
             )
         xx = descriptor
+        if self.remove_vaccum_contribution is not None:
+            # TODO: Idealy, the input for vaccum should be computed;
+            # we consider it as always zero for convenience.
+            # Needs a compute_input_stats for vaccum passed from the
+            # descriptor.
+            xx_zeros = np.zeros_like(xx)
+        else:
+            xx_zeros = None
         # check fparam dim, concate to input descriptor
         if self.numb_fparam > 0:
             assert fparam is not None, "fparam should not be None"
@@ -312,6 +325,11 @@
                 [xx, fparam],
                 axis=-1,
             )
+            if xx_zeros is not None:
+                xx_zeros = np.concatenate(
+                    [xx_zeros, fparam],
+                    axis=-1,
+                )
         # check aparam dim, concate to input descriptor
         if self.numb_aparam > 0:
             assert aparam is not None, "aparam should not be None"
@@ -326,6 +344,11 @@
                 [xx, aparam],
                 axis=-1,
             )
+            if xx_zeros is not None:
+                xx_zeros = np.concatenate(
+                    [xx_zeros, aparam],
+                    axis=-1,
+                )
 
         # calcualte the prediction
         if not self.mixed_types:
@@ -335,11 +358,19 @@
                     (atype == type_i).reshape([nf, nloc, 1]), [1, 1, net_dim_out]
                 )
                 atom_property = self.nets[(type_i,)](xx)
+                if self.remove_vaccum_contribution is not None and not (
+                    len(self.remove_vaccum_contribution) > type_i
+                    and not self.remove_vaccum_contribution[type_i]
+                ):
+                    assert xx_zeros is not None
+                    atom_property -= self.nets[(type_i,)](xx_zeros)
                 atom_property = atom_property + self.bias_atom_e[type_i]
                 atom_property = atom_property * mask
                 outs = outs + atom_property  # Shape is [nframes, natoms[0], 1]
         else:
             outs = self.nets[()](xx) + self.bias_atom_e[atype]
+            if xx_zeros is not None:
+                outs -= self.nets[()](xx_zeros)
         # nf x nloc
         exclude_mask = self.emask.build_type_exclude_mask(atype)
         # nf x nloc x nod

deepmd/dpmodel/fitting/invar_fitting.py

@@ -136,8 +136,6 @@ def __init__(
             raise NotImplementedError("use_aparam_as_mask is not implemented")
         if layer_name is not None:
             raise NotImplementedError("layer_name is not implemented")
-        if atom_ener is not None and atom_ener != []:
-            raise NotImplementedError("atom_ener is not implemented")
 
         self.dim_out = dim_out
         self.atom_ener = atom_ener
@@ -159,6 +157,9 @@ def __init__(
             spin=spin,
             mixed_types=mixed_types,
             exclude_types=exclude_types,
+            remove_vaccum_contribution=None
+            if atom_ener is None or len([x for x in atom_ener if x is not None]) == 0
+            else [x is not None for x in atom_ener],
         )
 
     def serialize(self) -> dict:

deepmd/pt/model/task/ener.py

@@ -124,6 +124,9 @@ def __init__(
             rcond=rcond,
             seed=seed,
             exclude_types=exclude_types,
+            remove_vaccum_contribution=None
+            if atom_ener is None or len([x for x in atom_ener if x is not None]) == 0
+            else [x is not None for x in atom_ener],
             **kwargs,
         )
 

deepmd/pt/model/task/fitting.py

@@ -246,7 +246,10 @@ class GeneralFitting(Fitting):
         Random seed.
     exclude_types: List[int]
         Atomic contributions of the excluded atom types are set zero.
-
+    remove_vaccum_contribution: List[bool], optional
+        Remove vaccum contribution before the bias is added. The list assigned each
+        type. If not mixed_types, only remove the vaccum contribution for the atom types
+        in the list.
     """
 
     def __init__(
@@ -265,6 +268,7 @@ def __init__(
         rcond: Optional[float] = None,
         seed: Optional[int] = None,
         exclude_types: List[int] = [],
+        remove_vaccum_contribution: Optional[List[bool]] = None,
         **kwargs,
     ):
         super().__init__()
@@ -282,6 +286,7 @@ def __init__(
         self.rcond = rcond
         # order matters, should be place after the assignment of ntypes
         self.reinit_exclude(exclude_types)
+        self.remove_vaccum_contribution = remove_vaccum_contribution
 
         net_dim_out = self._net_out_dim()
         # init constants
@@ -487,6 +492,14 @@ def _forward_common(
         aparam: Optional[torch.Tensor] = None,
     ):
         xx = descriptor
+        if self.remove_vaccum_contribution is not None:
+            # TODO: Idealy, the input for vaccum should be computed;
+            # we consider it as always zero for convenience.
+            # Needs a compute_input_stats for vaccum passed from the
+            # descriptor.
+            xx_zeros = torch.zeros_like(xx)
+        else:
+            xx_zeros = None
         nf, nloc, nd = xx.shape
         net_dim_out = self._net_out_dim()
 
@@ -515,6 +528,11 @@ def _forward_common(
                 [xx, fparam],
                 dim=-1,
             )
+            if xx_zeros is not None:
+                xx_zeros = torch.cat(
+                    [xx_zeros, fparam],
+                    dim=-1,
+                )
         # check aparam dim, concate to input descriptor
         if self.numb_aparam > 0:
             assert aparam is not None, "aparam should not be None"
@@ -534,6 +552,11 @@ def _forward_common(
                 [xx, aparam],
                 dim=-1,
             )
+            if xx_zeros is not None:
+                xx_zeros = torch.cat(
+                    [xx_zeros, aparam],
+                    dim=-1,
+                )
 
         outs = torch.zeros(
             (nf, nloc, net_dim_out),
@@ -542,6 +565,7 @@ def _forward_common(
         )  # jit assertion
         if self.old_impl:
             assert self.filter_layers_old is not None
+            assert xx_zeros is None
             if self.mixed_types:
                 atom_property = self.filter_layers_old[0](xx) + self.bias_atom_e[atype]
                 outs = outs + atom_property  # Shape is [nframes, natoms[0], 1]
@@ -557,6 +581,8 @@ def _forward_common(
                 atom_property = (
                     self.filter_layers.networks[0](xx) + self.bias_atom_e[atype]
                 )
+                if xx_zeros is not None:
+                    atom_property -= self.filter_layers.networks[0](xx_zeros)
                 outs = (
                     outs + atom_property
                 )  # Shape is [nframes, natoms[0], net_dim_out]
@@ -565,6 +591,14 @@ def _forward_common(
                     mask = (atype == type_i).unsqueeze(-1)
                     mask = torch.tile(mask, (1, 1, net_dim_out))
                     atom_property = ll(xx)
+                    if xx_zeros is not None:
+                        # must assert, otherwise jit is not happy
+                        assert self.remove_vaccum_contribution is not None
+                        if not (
+                            len(self.remove_vaccum_contribution) > type_i
+                            and not self.remove_vaccum_contribution[type_i]
+                        ):
+                            atom_property -= ll(xx_zeros)
                     atom_property = atom_property + self.bias_atom_e[type_i]
                     atom_property = atom_property * mask
                     outs = (

deepmd/tf/fit/ener.py

@@ -1003,7 +1003,7 @@ def serialize(self, suffix: str = "") -> dict:
             "rcond": self.rcond,
             "tot_ener_zero": self.tot_ener_zero,
             "trainable": self.trainable,
-            "atom_ener": self.atom_ener,
+            "atom_ener": self.atom_ener_v,
             "activation_function": self.activation_function_name,
             "precision": self.fitting_precision.name,
             "layer_name": self.layer_name,

source/tests/consistent/fitting/test_ener.py

@@ -43,6 +43,7 @@
     ("float64", "float32"),  # precision
     (True, False),  # mixed_types
     (0, 1),  # numb_fparam
+    ([], [-12345.6, None]),  # atom_ener
 )
 class TestEner(CommonTest, FittingTest, unittest.TestCase):
     @property
@@ -52,13 +53,15 @@
             precision,
             mixed_types,
             numb_fparam,
+            atom_ener,
         ) = self.param
         return {
             "neuron": [5, 5, 5],
             "resnet_dt": resnet_dt,
             "precision": precision,
             "numb_fparam": numb_fparam,
             "seed": 20240217,
+            "atom_ener": atom_ener,
         }
 
     @property
@@ -68,6 +71,7 @@
             precision,
             mixed_types,
             numb_fparam,
+            atom_ener,
         ) = self.param
         # TODO: mixed_types
         return mixed_types or CommonTest.skip_pt
@@ -79,6 +83,7 @@
             precision,
             mixed_types,
             numb_fparam,
+            atom_ener,
         ) = self.param
         return CommonTest.skip_pt
 
@@ -105,6 +110,7 @@
             precision,
             mixed_types,
             numb_fparam,
+            atom_ener,
         ) = self.param
         return {
             "ntypes": self.ntypes,
@@ -118,6 +124,7 @@
             precision,
             mixed_types,
             numb_fparam,
+            atom_ener,
         ) = self.param
         return self.build_tf_fitting(
             obj,
@@ -134,6 +141,7 @@
             precision,
             mixed_types,
             numb_fparam,
+            atom_ener,
         ) = self.param
         return (
             pt_obj(
@@ -154,6 +162,7 @@
             precision,
             mixed_types,
             numb_fparam,
+            atom_ener,
         ) = self.param
         return dp_obj(
             self.inputs,
@@ -175,6 +184,7 @@
             precision,
             mixed_types,
             numb_fparam,
+            atom_ener,
         ) = self.param
         if precision == "float64":
             return 1e-10
@@ -191,6 +201,7 @@
             precision,
             mixed_types,
             numb_fparam,
+            atom_ener,
         ) = self.param
         if precision == "float64":
             return 1e-10