def init_training_data(self):
"""
Prepare the training data by attaching delta values for training.
"""
raw_data = self.parent_dataset
sp_raw_data = convert_to_singlepoint(raw_data)
parent_ref_image = sp_raw_data[0].copy()
base_ref_image = compute_with_calc(sp_raw_data[:1], self.base_calc)[0]
self.refs = [parent_ref_image, base_ref_image]
self.delta_sub_calc = DeltaCalc(self.calcs, "sub", self.refs)
self.ensemble_sets, self.parent_dataset = bootstrap_ensemble(
compute_with_calc(sp_raw_data, self.delta_sub_calc))
def init_training_data(self):
"""
Prepare the training data by attaching delta values for training.
"""
raw_data = self.training_data
sp_raw_data = convert_to_singlepoint(raw_data)
parent_ref_image = sp_raw_data[0]
base_ref_image = compute_with_calc([parent_ref_image],
self.base_calc)[0]
self.refs = [parent_ref_image, base_ref_image]
self.delta_sub_calc = DeltaCalc(self.calcs, "sub", self.refs)
self.training_data = compute_with_calc(sp_raw_data,
self.delta_sub_calc)
def do_after_train(self):
"""
Executes after training the trainer in every active learning loop.
"""
trainer_calc = self.make_trainer_calc()
self.trained_calc = DeltaCalc([trainer_calc, self.base_calc], "add", self.refs)
self.atomistic_method.run(calc=self.trained_calc, filename=self.fn_label)
self.sample_candidates = list(
self.atomistic_method.get_trajectory(filename=self.fn_label)
)
final_point_image = [self.sample_candidates[-1]]
# print(final_point_image[0].get_positions())
final_point_evA = compute_with_calc(final_point_image, self.parent_calc)
self.final_point_force = np.max(np.abs(final_point_evA[0].get_forces()))
self.training_data += subtract_deltas(
final_point_evA, self.base_calc, self.refs
)
self.parent_calls += 1
# final_queries_db = ase.db.connect("final_queried_images.db")
random.seed(self.query_seeds[self.iterations - 1] + 1)
# write_to_db(final_queries_db, final_point_image)
if self.iterations == 0:
writer = TrajectoryWriter("final_images.traj", mode="w")
writer.write(final_point_image[0])
else:
writer = TrajectoryWriter("final_images.traj", mode="a")
writer.write(final_point_image[0])
self.terminate = self.check_terminate()
self.iterations += 1
def setUpClass(cls) -> None:
initial_structure = Icosahedron("Cu", 2)
initial_structure.rattle(0.1)
initial_structure.set_pbc(True)
initial_structure.set_cell([20, 20, 20])
EMT_initial_structure = initial_structure.copy()
parent_calc = EMT()
cls.emt_counter = CounterCalc(parent_calc)
EMT_initial_structure.set_calculator(cls.emt_counter)
cls.EMT_structure_optim = Relaxation(
EMT_initial_structure, BFGS, fmax=0.01, steps=30
)
cls.EMT_structure_optim.run(cls.emt_counter, "CuNP_emt")
offline_initial_structure = compute_with_calc(
[initial_structure.copy()], parent_calc
)[0]
Offline_relaxation = Relaxation(
offline_initial_structure, BFGS, fmax=0.01, steps=30, maxstep=0.05
)
cls.offline_learner, cls.trained_calc, cls.Offline_traj = run_offline_al(
Offline_relaxation,
[offline_initial_structure],
"CuNP_offline_al",
parent_calc,
)
cls.EMT_image = cls.EMT_structure_optim.get_trajectory("CuNP_emt")[-1]
cls.EMT_image.set_calculator(parent_calc)
cls.offline_final_structure_AL = cls.Offline_traj[-1]
cls.offline_final_structure_AL.set_calculator(cls.trained_calc)
cls.offline_final_structure_EMT = cls.Offline_traj[-1]
cls.offline_final_structure_EMT.set_calculator(parent_calc)
cls.description = "CuNP"
return super().setUpClass()
def query_data(self):
"""
Queries data from a list of images. Calculates the properties
and adds them to the training data.
"""
random.seed(self.query_seeds[self.iterations - 1])
random_queried_images, min_force_image = self.query_func()
self.training_data += compute_with_calc(
random_queried_images, self.delta_sub_calc
)
min_image_parent = compute_with_calc([min_force_image], self.parent_calc)[0]
self.final_point_force = np.max(np.abs(min_image_parent.get_forces()))
self.training_data += subtract_deltas(
[min_image_parent], self.base_calc, self.refs
)
def add_data(self, queried_images, query_idx):
self.new_dataset = compute_with_calc(queried_images,
self.delta_sub_calc)
self.training_data += self.new_dataset
self.parent_calls += len(self.new_dataset)
un_delta_new_dataset = []
for image in self.new_dataset:
add_delta_calc = DeltaCalc([image.calc, self.base_calc], "add",
self.refs)
[un_delta_image] = compute_with_calc([image], add_delta_calc)
un_delta_new_dataset.append(un_delta_image)
for i in range(len(un_delta_new_dataset)):
image = un_delta_new_dataset[i]
idx = None
if query_idx is not None:
idx = query_idx[i]
energy = image.get_potential_energy(apply_constraint=False)
forces = image.get_forces(apply_constraint=False)
constrained_forces = image.get_forces()
fmax = np.sqrt((constrained_forces**2).sum(axis=1).max())
info = {
"check": True,
"energy": energy,
"forces": forces,
"fmax": fmax,
"ml_energy": None,
"ml_forces": None,
"ml_fmax": None,
"parent_energy": energy,
"parent_forces": forces,
"parent_fmax": fmax,
"force_uncertainty": image.info.get("max_force_stds", None),
"energy_uncertainty": image.info.get("energy_stds", None),
"dyn_uncertainty_tol": None,
"stat_uncertain_tol": None,
"tolerance": None,
"parent_calls": self.parent_calls,
"trained_on": True,
"query_idx": idx,
"substep": idx,
}
self.logger.write(image, info)
return un_delta_new_dataset
def query_data(self):
"""
Queries data from a list of images. Calculates the properties
and adds them to the training data.
"""
random.seed(self.query_seeds[self.iterations - 1])
queried_images = self.query_func()
self.training_data += compute_with_calc(queried_images, self.delta_sub_calc)
def init_training_data(self):
"""
Prepare the training data by attaching delta values for training.
"""
raw_data = self.training_data
sp_raw_data = convert_to_singlepoint(raw_data)
parent_ref_image = sp_raw_data[0]
base_ref_image = compute_with_calc([parent_ref_image],
self.base_calc)[0]
self.refs = [parent_ref_image, base_ref_image]
self.delta_sub_calc = DeltaCalc(self.calcs, "sub", self.refs)
self.training_data = []
for image in sp_raw_data:
sp_calc = image.get_calculator()
sp_calc.implemented_properties = ["energy", "forces"]
sp_delta_calc = DeltaCalc([sp_calc, self.base_calc], "sub",
self.refs)
self.training_data += compute_with_calc([image], sp_delta_calc)
def query_data(self):
"""
Queries data from a list of images. Calculates the properties and adds them to the training data.
Parameters
----------
sample_candidates: list
List of ase atoms objects to query from.
"""
queried_images = self.query_func()
self.training_data += compute_with_calc(queried_images,
self.delta_sub_calc)
def init_refs(self, initial_structure):
self.parent_ref = initial_structure.copy()
self.parent_ref.calc = deepcopy(initial_structure.calc)
self.base_ref = compute_with_calc([initial_structure.copy()],
self.base_calc)[0]
self.refs = [self.parent_ref, self.base_ref]
self.add_delta_calc = DeltaCalc(
[self.ml_potential, self.base_calc],
"add",
self.refs,
)
def check_final_force(self):
final_point_image = [self.sample_candidates[-1]]
final_point_evA = compute_with_calc(final_point_image, self.delta_sub_calc)
self.final_point_force = final_point_evA[0].info["parent fmax"]
print("final point fmax: ", self.final_point_force)
# only add the last image to training data if the last image is safe to query
if final_point_evA[0].info["parent energy"] < self.initial_image_energy:
self.training_data += final_point_evA
random.seed(self.query_seeds[self.iterations - 1] + 1)
queries_db = ase.db.connect("queried_images.db")
parent_E = final_point_evA[0].info["parent energy"]
base_E = final_point_evA[0].info["base energy"]
write_to_db(queries_db, final_point_evA, "final image", parent_E, base_E)
self.parent_calls += 1
def init_refs(self, initial_structure):
# TODO: raise error if no organic element is found in structure
self.parent_ref = initial_structure.copy()
self.parent_ref.calc = deepcopy(initial_structure.calc)
self.adsorbate_idx = np.array(
[
atom.symbol in set(["C", "H", "O", "N"])
for atom in initial_structure.copy()
]
)
self.base_ref = compute_with_calc(
[initial_structure.copy()[self.adsorbate_idx]], self.base_calc
)[0]
self.refs = [self.parent_ref, self.base_ref]
self.add_delta_calc = DeltaCalc(
[self.ml_potential, self.base_calc],
"add",
self.refs,
)
def quantify_uncertainty(traj, model_calc):
parent_images = copy_images(traj)
model_images = compute_with_calc(traj, model_calc)
initial_energy_diff = (model_images[0].get_potential_energy() -
parent_images[0].get_potential_energy())
true_forces = []
predicted_forces = []
force_uncertainties = []
true_energies = []
predicted_energies = []
energy_uncertainties = []
for pi, mi in zip(parent_images, model_images):
true_forces.append(np.sqrt((pi.get_forces()**2).sum(axis=1).max()))
predicted_forces.append(np.sqrt(
(mi.get_forces()**2).sum(axis=1).max()))
force_uncertainties.append(mi.info["max_force_stds"])
if math.isnan(force_uncertainties[-1]):
raise ValueError("NaN uncertainty")
true_energies.append(pi.get_potential_energy())
predicted_energies.append(mi.get_potential_energy() -
initial_energy_diff)
energy_uncertainties.append(mi.info["energy_stds"])
force_scores = get_all_metrics(
np.array(predicted_forces),
np.array(force_uncertainties),
np.array(true_forces),
verbose=False,
)
energy_scores = get_all_metrics(
np.array(predicted_energies),
np.array(energy_uncertainties),
np.array(true_energies),
verbose=False,
)
return force_scores, energy_scores
def init_training_data(self):
"""
Prepare the training data by attaching delta values for training.
"""
# setup delta sub calc as defacto parent calc for all queries
parent_ref_image = self.atomistic_method.initial_geometry
base_ref_image = compute_with_calc([parent_ref_image],
self.base_calc)[0]
self.refs = [parent_ref_image, base_ref_image]
self.delta_sub_calc = DeltaCalc(self.calcs, "sub", self.refs)
# move training data into raw data for computing with delta calc
raw_data = []
for image in self.training_data:
raw_data.append(image)
# run a trajectory with no training data: just the base model to sample from
self.training_data = []
self.fn_label = f"{self.file_dir}{self.filename}_iter_{self.iterations}"
self.do_after_train()
# add initial data to training dataset
self.add_data(raw_data, None)
self.initial_image_energy = self.refs[0].get_potential_energy()
# "logger": True,
"single-threaded": True,
},
}
dbname = "CuNP_oal"
trainer = AtomsTrainer(config)
checkpoint_path = "/home/jovyan/working/ocp/data/pretrained/s2ef/dimenetpp_2M.pt"
model_path = (
"/home/jovyan/working/ocp-dev/configs/s2ef/2M/dimenet_plus_plus/dpp.yml"
)
base_calc = OCPModel(model_path=model_path,
checkpoint_path=checkpoint_path)
# base_initial_structure = initial_structure.copy()
base_initial_structure = compute_with_calc([initial_structure.copy()],
base_calc)[0]
# base_initial_structure.set_calculator(base_calc)
delta_calc = DeltaCalc(
[parent_calc, base_calc],
"sub",
[OAL_initial_structure, base_initial_structure],
)
ml_potential = AmptorchEnsembleCalc(trainer, learner_params["n_ensembles"])
online_calc = OnlineLearner(
learner_params,
images,
ml_potential,
delta_calc,