feat: handle masked forces in test (#4893)

<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit

- New Features
- Added per-atom weighting for force evaluation: computes and reports
weighted MAE/RMSE alongside unweighted metrics, includes weighted
metrics in system-average summaries, logs weighted force metrics, and
safely handles zero-weight cases. Also propagates the per-atom weight
field into reporting.

- Tests
- Added end-to-end tests validating weighted vs unweighted force
MAE/RMSE and verifying evaluator outputs when using per-atom weight
masks.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

Author: caic99

deepmd/entrypoints/test.py

@@ -291,6 +291,7 @@ def test_ener(
 
     data.add("energy", 1, atomic=False, must=False, high_prec=True)
     data.add("force", 3, atomic=True, must=False, high_prec=False)
+    data.add("atom_pref", 1, atomic=True, must=False, high_prec=False, repeat=3)
     data.add("virial", 9, atomic=False, must=False, high_prec=False)
     if dp.has_efield:
         data.add("efield", 3, atomic=True, must=True, high_prec=False)
@@ -313,6 +314,7 @@ def test_ener(
     find_force = test_data.get("find_force")
     find_virial = test_data.get("find_virial")
     find_force_mag = test_data.get("find_force_mag")
+    find_atom_pref = test_data.get("find_atom_pref")
     mixed_type = data.mixed_type
     natoms = len(test_data["type"][0])
     nframes = test_data["box"].shape[0]
@@ -419,6 +421,16 @@ def test_ener(
     diff_f = force - test_data["force"][:numb_test]
     mae_f = mae(diff_f)
     rmse_f = rmse(diff_f)
+    size_f = diff_f.size
+    if find_atom_pref == 1:
+        atom_weight = test_data["atom_pref"][:numb_test]
+        weight_sum = np.sum(atom_weight)
+        if weight_sum > 0:
+            mae_fw = np.sum(np.abs(diff_f) * atom_weight) / weight_sum
+            rmse_fw = np.sqrt(np.sum(diff_f * diff_f * atom_weight) / weight_sum)
+        else:
+            mae_fw = 0.0
+            rmse_fw = 0.0
     diff_v = virial - test_data["virial"][:numb_test]
     mae_v = mae(diff_v)
     rmse_v = rmse(diff_v)
@@ -453,8 +465,13 @@ def test_ener(
     if not out_put_spin and find_force == 1:
         log.info(f"Force  MAE         : {mae_f:e} eV/A")
         log.info(f"Force  RMSE        : {rmse_f:e} eV/A")
-        dict_to_return["mae_f"] = (mae_f, force.size)
-        dict_to_return["rmse_f"] = (rmse_f, force.size)
+        dict_to_return["mae_f"] = (mae_f, size_f)
+        dict_to_return["rmse_f"] = (rmse_f, size_f)
+        if find_atom_pref == 1:
+            log.info(f"Force weighted MAE : {mae_fw:e} eV/A")
+            log.info(f"Force weighted RMSE: {rmse_fw:e} eV/A")
+            dict_to_return["mae_fw"] = (mae_fw, weight_sum)
+            dict_to_return["rmse_fw"] = (rmse_fw, weight_sum)
     if out_put_spin and find_force == 1:
         log.info(f"Force atom MAE      : {mae_fr:e} eV/A")
         log.info(f"Force atom RMSE     : {rmse_fr:e} eV/A")
@@ -600,6 +617,9 @@ def print_ener_sys_avg(avg: dict[str, float]) -> None:
     if "rmse_f" in avg:
         log.info(f"Force  MAE         : {avg['mae_f']:e} eV/A")
         log.info(f"Force  RMSE        : {avg['rmse_f']:e} eV/A")
+        if "rmse_fw" in avg:
+            log.info(f"Force weighted MAE : {avg['mae_fw']:e} eV/A")
+            log.info(f"Force weighted RMSE: {avg['rmse_fw']:e} eV/A")
     else:
         log.info(f"Force atom MAE      : {avg['mae_fr']:e} eV/A")
         log.info(f"Force spin MAE      : {avg['mae_fm']:e} eV/uB")

source/tests/pt/test_dp_test.py

@@ -15,12 +15,19 @@
 import torch
 
 from deepmd.entrypoints.test import test as dp_test
+from deepmd.entrypoints.test import test_ener as dp_test_ener
+from deepmd.infer.deep_eval import (
+    DeepEval,
+)
 from deepmd.pt.entrypoints.main import (
     get_trainer,
 )
 from deepmd.pt.utils.utils import (
     to_numpy_array,
 )
+from deepmd.utils.data import (
+    DeepmdData,
+)
 
 from .model.test_permutation import (
     model_property,
@@ -140,6 +147,98 @@ def setUp(self) -> None:
             json.dump(self.config, fp, indent=4)
 
 
+class TestDPTestForceWeight(DPTest, unittest.TestCase):
+    def setUp(self) -> None:
+        self.detail_file = "test_dp_test_force_weight_detail"
+        input_json = str(Path(__file__).parent / "water/se_atten.json")
+        with open(input_json) as f:
+            self.config = json.load(f)
+        self.config["training"]["numb_steps"] = 1
+        self.config["training"]["save_freq"] = 1
+        system_dir = self._prepare_weighted_system()
+        data_file = [system_dir]
+        self.config["training"]["training_data"]["systems"] = data_file
+        self.config["training"]["validation_data"]["systems"] = data_file
+        self.config["model"] = deepcopy(model_se_e2_a)
+        self.system_dir = system_dir
+        self.input_json = "test_dp_test_force_weight.json"
+        with open(self.input_json, "w") as fp:
+            json.dump(self.config, fp, indent=4)
+
+    def _prepare_weighted_system(self) -> str:
+        src = Path(__file__).parent / "water/data/single"
+        tmp_dir = tempfile.mkdtemp()
+        shutil.copytree(src, tmp_dir, dirs_exist_ok=True)
+        set_dir = Path(tmp_dir) / "set.000"
+        forces = np.load(set_dir / "force.npy")
+        forces[0, :3] += 1.0
+        forces[0, -3:] += 10.0
+        np.save(set_dir / "force.npy", forces)
+        natoms = forces.shape[1] // 3
+        atom_pref = np.ones((forces.shape[0], natoms), dtype=forces.dtype)
+        atom_pref[:, 0] = 2.0
+        atom_pref[:, -1] = 0.0
+        np.save(set_dir / "atom_pref.npy", atom_pref)
+        return tmp_dir
+
+    def test_force_weight(self) -> None:
+        trainer = get_trainer(deepcopy(self.config))
+        with torch.device("cpu"):
+            trainer.get_data(is_train=False)
+        model = torch.jit.script(trainer.model)
+        tmp_model = tempfile.NamedTemporaryFile(delete=False, suffix=".pth")
+        torch.jit.save(model, tmp_model.name)
+        dp = DeepEval(tmp_model.name)
+        data = DeepmdData(
+            self.system_dir,
+            set_prefix="set",
+            shuffle_test=False,
+            type_map=dp.get_type_map(),
+            sort_atoms=False,
+        )
+        err = dp_test_ener(
+            dp,
+            data,
+            self.system_dir,
+            numb_test=1,
+            detail_file=None,
+            has_atom_ener=False,
+        )
+        test_data = data.get_test()
+        coord = test_data["coord"].reshape([1, -1])
+        box = test_data["box"][:1]
+        atype = test_data["type"][0]
+        ret = dp.eval(
+            coord,
+            box,
+            atype,
+            fparam=None,
+            aparam=None,
+            atomic=False,
+            efield=None,
+            mixed_type=False,
+            spin=None,
+        )
+        force_pred = ret[1].reshape([1, -1])
+        force_true = test_data["force"][:1]
+        weight = test_data["atom_pref"][:1]
+        diff = force_pred - force_true
+        mae_unweighted = np.sum(np.abs(diff)) / diff.size
+        rmse_unweighted = np.sqrt(np.sum(diff * diff) / diff.size)
+        denom = weight.sum()
+        mae_weighted = np.sum(np.abs(diff) * weight) / denom
+        rmse_weighted = np.sqrt(np.sum(diff * diff * weight) / denom)
+        np.testing.assert_allclose(err["mae_f"][0], mae_unweighted)
+        np.testing.assert_allclose(err["rmse_f"][0], rmse_unweighted)
+        np.testing.assert_allclose(err["mae_fw"][0], mae_weighted)
+        np.testing.assert_allclose(err["rmse_fw"][0], rmse_weighted)
+        os.unlink(tmp_model.name)
+
+    def tearDown(self) -> None:
+        super().tearDown()
+        shutil.rmtree(self.system_dir)
+
+
 class TestDPTestPropertySeA(unittest.TestCase):
     def setUp(self) -> None:
         self.detail_file = "test_dp_test_property_detail"