def periodic_0th_bfgs_step_test():
###########################################################################
# Making the list of images
images = [
Atoms(symbols='PdOPd',
pbc=np.array([True, False, False], dtype=bool),
cell=np.array([[2., 0., 0.], [0., 2., 0.], [0., 0., 2.]]),
positions=np.array([[0.5, 1., 0.5], [1., 0.5, 1.],
[1.5, 1.5, 1.5]])),
Atoms(symbols='PdO',
pbc=np.array([True, True, False], dtype=bool),
cell=np.array([[2., 0., 0.], [0., 2., 0.], [0., 0., 2.]]),
positions=np.array([[0.5, 1., 0.5], [1., 0.5, 1.]])),
Atoms(symbols='Cu',
pbc=np.array([True, True, False], dtype=bool),
cell=np.array([[1.8, 0., 0.], [0., 1.8, 0.], [0., 0., 1.8]]),
positions=np.array([[0., 0., 0.]]))
]
for image in images:
image.set_calculator(EMT())
image.get_potential_energy(apply_constraint=False)
image.get_forces(apply_constraint=False)
###########################################################################
# Parameters
Gs = {
'O': [{
'type': 'G2',
'element': 'Pd',
'eta': 0.8
}, {
'type': 'G4',
'elements': ['O', 'Pd'],
'eta': 0.3,
'gamma': 0.6,
'zeta': 0.5
}],
'Pd': [{
'type': 'G2',
'element': 'Pd',
'eta': 0.2
}, {
'type': 'G4',
'elements': ['Pd', 'Pd'],
'eta': 0.9,
'gamma': 0.75,
'zeta': 1.5
}],
'Cu': [{
'type': 'G2',
'element': 'Cu',
'eta': 0.8
}, {
'type': 'G4',
'elements': ['Cu', 'Cu'],
'eta': 0.3,
'gamma': 0.6,
'zeta': 0.5
}]
}
hiddenlayers = {'O': (2), 'Pd': (2), 'Cu': (2)}
weights = OrderedDict([
('O',
OrderedDict([(1, np.matrix([[-2.0, 6.0], [3.0, -3.0], [1.5, -0.9]])),
(2, np.matrix([[5.5], [3.6], [1.4]]))])),
('Pd',
OrderedDict([(1, np.matrix([[-1.0, 3.0], [2.0, 4.2], [1.0, -0.7]])),
(2, np.matrix([[4.0], [0.5], [3.0]]))])),
('Cu',
OrderedDict([(1, np.matrix([[0.0, 1.0], [-1.0, -2.0], [2.5, -1.9]])),
(2, np.matrix([[0.5], [1.6], [-1.4]]))]))
])
scalings = OrderedDict([
('O', OrderedDict([('intercept', -2.3), ('slope', 4.5)])),
('Pd', OrderedDict([('intercept', 1.6), ('slope', 2.5)])),
('Cu', OrderedDict([('intercept', -0.3), ('slope', -0.5)]))
])
###########################################################################
# Correct values
correct_cost = 8004.292841472513
correct_energy_rmse = 43.736001940333836
correct_force_rmse = 137.4099476110887
correct_der_cost_fxn = [
0.0814166874813534, 0.03231235582927526, 0.04388650395741291,
0.017417514465933048, 0.0284312765975806, 0.011283700608821421,
0.09416957265766414, -0.12322258890997816, 0.12679918754162384,
63.5396007548815, 0.016247700195771732, -86.62639558745185,
-0.017777528287386473, 86.22415217678898, 0.017745913074805372,
104.58358033260711, -96.7328020983672, -99.09843648854351,
-8.302880631971407, -1.2590007162073242, 8.3028773468822,
1.258759884181224, -8.302866610677315, -1.2563833805673688,
28.324298392677846, 28.09315509472324, -29.378744559315365,
-11.247473567051799, 11.119951466671642, -87.08582317485761,
-20.93948523898559, -125.73267675714658, -35.13852440758523
]
###########################################################################
# Testing pure-python and fortran versions of Gaussian-neural on different
# number of processes
for global_search in [None, 'SA']:
for fortran in [False, True]:
for extend_variables in [False, True]:
for data_format in ['db', 'json']:
for save_memory in [False]:
for cores in range(1, 5):
string = 'CuOPdbp/2/%s-%s-%s-%s-%s-%i'
label = string % (global_search, fortran,
extend_variables, data_format,
save_memory, cores)
if global_search is 'SA':
gs = \
SimulatedAnnealing(temperature=10, steps=5)
elif global_search is None:
gs = None
print label
calc = Amp(descriptor=Gaussian(cutoff=4., Gs=Gs),
regression=NeuralNetwork(
hiddenlayers=hiddenlayers,
weights=weights,
scalings=scalings,
activation='tanh',
),
fortran=fortran,
label=label)
calc.train(images=images,
energy_goal=10.**10.,
force_goal=10.**10,
force_coefficient=0.04,
cores=cores,
data_format=data_format,
save_memory=save_memory,
global_search=gs,
extend_variables=extend_variables)
assert (abs(calc.cost_function - correct_cost) <
10.**(-7.)), \
'The calculated value of cost function is \
wrong!'
assert (abs(calc.energy_per_atom_rmse -
correct_energy_rmse) < 10.**(-10.)), \
'The calculated value of energy per atom RMSE \
is wrong!'
assert (abs(calc.force_rmse - correct_force_rmse) <
10 ** (-8.)), \
'The calculated value of force RMSE is wrong!'
for _ in range(len(correct_der_cost_fxn)):
assert(abs(calc.der_variables_cost_function[
_] -
correct_der_cost_fxn[_]) < 10 ** (-8)), \
'The calculated value of cost function \
derivative is wrong!'
dblabel = label
secondlabel = '_' + label
calc = Amp(descriptor=Gaussian(cutoff=4., Gs=Gs),
regression=NeuralNetwork(
hiddenlayers=hiddenlayers,
weights=weights,
scalings=scalings,
activation='tanh',
),
fortran=fortran,
label=secondlabel,
dblabel=dblabel)
calc.train(images=images,
energy_goal=10.**10.,
force_goal=10.**10,
force_coefficient=0.04,
cores=cores,
data_format=data_format,
save_memory=save_memory,
global_search=gs,
extend_variables=extend_variables)
assert (abs(calc.cost_function - correct_cost) <
10.**(-7.)), \
'The calculated value of cost function is \
wrong!'
assert (abs(calc.energy_per_atom_rmse -
correct_energy_rmse) < 10.**(-10.)), \
'The calculated value of energy per atom RMSE \
is wrong!'
assert (abs(calc.force_rmse - correct_force_rmse) <
10 ** (-8.)), \
'The calculated value of force RMSE is wrong!'
for _ in range(len(correct_der_cost_fxn)):
assert(abs(calc.der_variables_cost_function[
_] -
correct_der_cost_fxn[_] < 10 ** (-8))), \
'The calculated value of cost function \
def non_periodic_0th_bfgs_step_test():
pwd = os.getcwd()
os.mkdir(os.path.join(pwd, 'CuOPdbp'))
os.mkdir(os.path.join(pwd, '_CuOPdbp'))
os.mkdir(os.path.join(pwd, 'CuOPdbp/0'))
os.mkdir(os.path.join(pwd, '_CuOPdbp/0'))
os.mkdir(os.path.join(pwd, 'CuOPdbp/1'))
os.mkdir(os.path.join(pwd, '_CuOPdbp/1'))
os.mkdir(os.path.join(pwd, 'CuOPdbp/2'))
os.mkdir(os.path.join(pwd, '_CuOPdbp/2'))
###########################################################################
# Making the list of periodic image
images = [
Atoms(symbols='PdOPd2',
pbc=np.array([False, False, False], dtype=bool),
cell=np.array([[1., 0., 0.], [0., 1., 0.], [0., 0., 1.]]),
positions=np.array([[0., 0., 0.], [0., 2., 0.], [0., 0., 3.],
[1., 0., 0.]])),
Atoms(symbols='PdOPd2',
pbc=np.array([False, False, False], dtype=bool),
cell=np.array([[1., 0., 0.], [0., 1., 0.], [0., 0., 1.]]),
positions=np.array([[0., 1., 0.], [1., 2., 1.], [-1., 1., 2.],
[1., 3., 2.]])),
Atoms(symbols='PdO',
pbc=np.array([False, False, False], dtype=bool),
cell=np.array([[1., 0., 0.], [0., 1., 0.], [0., 0., 1.]]),
positions=np.array([[2., 1., -1.], [1., 2., 1.]])),
Atoms(symbols='Pd2O',
pbc=np.array([False, False, False], dtype=bool),
cell=np.array([[1., 0., 0.], [0., 1., 0.], [0., 0., 1.]]),
positions=np.array([[-2., -1., -1.], [1., 2., 1.], [3., 4.,
4.]])),
Atoms(symbols='Cu',
pbc=np.array([False, False, False], dtype=bool),
cell=np.array([[1., 0., 0.], [0., 1., 0.], [0., 0., 1.]]),
positions=np.array([[0., 0., 0.]]))
]
for image in images:
image.set_calculator(EMT())
image.get_potential_energy(apply_constraint=False)
image.get_forces(apply_constraint=False)
###########################################################################
# Parameters
Gs = {
'O': [{
'type': 'G2',
'element': 'Pd',
'eta': 0.8
}, {
'type': 'G4',
'elements': ['Pd', 'Pd'],
'eta': 0.2,
'gamma': 0.3,
'zeta': 1
}, {
'type': 'G4',
'elements': ['O', 'Pd'],
'eta': 0.3,
'gamma': 0.6,
'zeta': 0.5
}],
'Pd': [{
'type': 'G2',
'element': 'Pd',
'eta': 0.2
}, {
'type': 'G4',
'elements': ['Pd', 'Pd'],
'eta': 0.9,
'gamma': 0.75,
'zeta': 1.5
}, {
'type': 'G4',
'elements': ['O', 'Pd'],
'eta': 0.4,
'gamma': 0.3,
'zeta': 4
}],
'Cu': [{
'type': 'G2',
'element': 'Cu',
'eta': 0.8
}, {
'type': 'G4',
'elements': ['Cu', 'O'],
'eta': 0.2,
'gamma': 0.3,
'zeta': 1
}, {
'type': 'G4',
'elements': ['Cu', 'Cu'],
'eta': 0.3,
'gamma': 0.6,
'zeta': 0.5
}]
}
hiddenlayers = {'O': (2), 'Pd': (2), 'Cu': (2)}
weights = OrderedDict([
('O',
OrderedDict([(1,
np.matrix([[-2.0, 6.0], [3.0, -3.0], [1.5, -0.9],
[-2.5, -1.5]])),
(2, np.matrix([[5.5], [3.6], [1.4]]))])),
('Pd',
OrderedDict([(1,
np.matrix([[-1.0, 3.0], [2.0, 4.2], [1.0, -0.7],
[-3.0, 2.0]])),
(2, np.matrix([[4.0], [0.5], [3.0]]))])),
('Cu',
OrderedDict([(1,
np.matrix([[0.0, 1.0], [-1.0, -2.0], [2.5, -1.9],
[-3.5, 0.5]])),
(2, np.matrix([[0.5], [1.6], [-1.4]]))]))
])
scalings = OrderedDict([
('O', OrderedDict([('intercept', -2.3), ('slope', 4.5)])),
('Pd', OrderedDict([('intercept', 1.6), ('slope', 2.5)])),
('Cu', OrderedDict([('intercept', -0.3), ('slope', -0.5)]))
])
###########################################################################
# Correct values
correct_cost = 7144.810783950215
correct_energy_rmse = 24.318837496017185
correct_force_rmse = 144.70282475062052
correct_der_cost_fxn = [
0, 0, 0, 0, 0, 0, 0.01374139170953901, 0.36318423812749656,
0.028312691567496464, 0.6012336354445753, 0.9659002689921986,
-1.2897770059416218, -0.5718960935176884, -2.6425667221503035,
-1.1960399246712894, 0, 0, -2.7256379713943852, -0.9080181026559658,
-0.7739948323247023, -0.2915789426043727, -2.05998290443513,
-0.6156374289747903, -0.0060865174621348985, -0.8296785483640939,
0.0008092646748983969, 0.041613027034688874, 0.003426469079592851,
-0.9578004568876517, -0.006281929608090211, -0.28835884773094056,
-4.2457774110285245, -4.317412094174614, -8.02385959091948,
-3.240512651984099, -27.289862194996896, -26.8177742762254,
-82.45107056053345, -80.6816768350809
]
###########################################################################
# Testing pure-python and fortran versions of Gaussian-neural on different
# number of processes
for global_search in [None, 'SA']:
for fortran in [False, True]:
for extend_variables in [False, True]:
for data_format in ['db', 'json']:
for save_memory in [False]:
for cores in range(1, 7):
string = 'CuOPdbp/0/%s-%s-%s-%s-%s-%i'
label = string % (global_search, fortran,
extend_variables, data_format,
save_memory, cores)
if global_search is 'SA':
gs = \
SimulatedAnnealing(temperature=10, steps=5)
elif global_search is None:
gs = None
print label
calc = Amp(descriptor=Gaussian(cutoff=6.5, Gs=Gs),
regression=NeuralNetwork(
hiddenlayers=hiddenlayers,
weights=weights,
scalings=scalings,
activation='sigmoid',
),
fortran=fortran,
label=label)
calc.train(images=images,
energy_goal=10.**10.,
force_goal=10.**10.,
force_coefficient=0.04,
cores=cores,
data_format=data_format,
save_memory=save_memory,
global_search=gs,
extend_variables=extend_variables)
assert (abs(calc.cost_function - correct_cost) <
10.**(-5.)), \
'The calculated value of cost function is \
wrong!'
assert (abs(calc.energy_per_atom_rmse -
correct_energy_rmse) <
10.**(-10.)), \
'The calculated value of energy per atom RMSE \
is wrong!'
assert (abs(calc.force_rmse - correct_force_rmse) <
10 ** (-7)), \
'The calculated value of force RMSE is wrong!'
for _ in range(len(correct_der_cost_fxn)):
assert(abs(calc.der_variables_cost_function[
_] - correct_der_cost_fxn[_]) <
10 ** (-9)), \
'The calculated value of cost function \
derivative is wrong!'
dblabel = label
secondlabel = '_' + label
calc = Amp(descriptor=Gaussian(cutoff=6.5, Gs=Gs),
regression=NeuralNetwork(
hiddenlayers=hiddenlayers,
weights=weights,
scalings=scalings,
activation='sigmoid',
),
fortran=fortran,
label=secondlabel,
dblabel=dblabel)
calc.train(images=images,
energy_goal=10.**10.,
force_goal=10.**10.,
force_coefficient=0.04,
cores=cores,
data_format=data_format,
save_memory=save_memory,
global_search=gs,
extend_variables=extend_variables)
assert (abs(calc.cost_function - correct_cost) <
10.**(-5.)), \
'The calculated value of cost function is \
wrong!'
assert (abs(calc.energy_per_atom_rmse -
correct_energy_rmse) <
10.**(-10.)), \
'The calculated value of energy per atom RMSE \
is wrong!'
assert (abs(calc.force_rmse - correct_force_rmse) <
10 ** (-7)), \
'The calculated value of force RMSE is wrong!'
for _ in range(len(correct_der_cost_fxn)):
assert(abs(calc.der_variables_cost_function[
_] - correct_der_cost_fxn[_] <
10 ** (-9))), \
'The calculated value of cost function \
def test():
pwd = os.getcwd()
os.mkdir(os.path.join(pwd, 'CuOPdnone'))
os.mkdir(os.path.join(pwd, '_CuOPdnone'))
###########################################################################
# Parameters
weights = OrderedDict([(1,
np.array([[1., 2.5], [0., 1.5], [0.,
-1.5], [3., 9.],
[1., -2.5], [2., 3.], [2.,
2.5], [3., 0.],
[-3.5, 1.], [5., 3.], [-2., 2.5],
[-4., 4.], [0., 0.]])),
(2, np.array([[1.], [2.], [0.]])),
(3, np.array([[3.5], [0.]]))])
scalings = OrderedDict([('intercept', 3.), ('slope', 2.)])
images = generate_images()
###########################################################################
# Testing pure-python and fortran versions of Gaussian-neural on different
# number of processes
for global_search in [None, 'SA']:
for fortran in [False, True]:
for extend_variables in [False, True]:
for data_format in ['db', 'json']:
for save_memory in [False]:
for cores in range(1, 7):
string = 'CuOPdnone/%s-%s-%s-%s-%s-%i'
label = string % (global_search, fortran,
extend_variables, data_format,
save_memory, cores)
if global_search is 'SA':
gs = \
SimulatedAnnealing(temperature=10, steps=5)
elif global_search is None:
gs = None
print label
calc = Amp(
descriptor=None,
regression=NeuralNetwork(
hiddenlayers=(2, 1),
activation='tanh',
weights=weights,
scalings=scalings,
),
fortran=fortran,
label=label,
)
calc.train(images=images,
energy_goal=10.**10.,
force_goal=10.**10.,
force_coefficient=0.04,
cores=cores,
data_format=data_format,
save_memory=save_memory,
global_search=gs,
extend_variables=extend_variables)
# Check for consistency between the two models
assert (abs(calc.cost_function - cost_function) <
10.**(-5.)), \
'The calculated value of cost function is \
wrong!'
assert (abs(calc.energy_per_atom_rmse -
energy_rmse) <
10.**(-5.)), \
'The calculated value of energy per atom RMSE \
is wrong!'
assert (abs(calc.force_rmse - force_rmse) <
10 ** (-5)), \
'The calculated value of force RMSE is wrong!'
dblabel = label
secondlabel = '_' + label
calc = Amp(descriptor=None,
regression=NeuralNetwork(
hiddenlayers=(2, 1),
activation='tanh',
weights=weights,
scalings=scalings,
),
fortran=fortran,
label=secondlabel,
dblabel=dblabel)
calc.train(images=images,
energy_goal=10.**10.,
force_goal=10.**10.,
force_coefficient=0.04,
cores=cores,
data_format=data_format,
save_memory=save_memory,
global_search=gs,
extend_variables=extend_variables)
# Check for consistency between the two models
assert (abs(calc.cost_function - cost_function) <
10.**(-5.)), \
'The calculated value of cost function is \
wrong!'
assert (abs(calc.energy_per_atom_rmse -
energy_rmse) <
10.**(-5.)), \
'The calculated value of energy per atom RMSE \
is wrong!'
assert (abs(calc.force_rmse - force_rmse) <
10 ** (-5)), \
'The calculated value of force RMSE is wrong!'
#!/usr/bin/env python
from amp import Amp
from amp.descriptor import Gaussian
from amp.regression import NeuralNetwork
from ase.db import connect
from amp import SimulatedAnnealing
db = connect('../../../database/master.db')
images = []
for d in db.select('train_set=True'):
atoms = db.get_atoms(d.id)
del atoms.constraints
images += [atoms]
for n in [2, 3]:
calc = Amp(label='./',
dblabel='../../',
descriptor=Gaussian(cutoff=6.5),
regression=NeuralNetwork(hiddenlayers=(2, n)))
calc.train(images=images,
data_format='db',
cores=4,
energy_goal=1e-2,
force_goal=1e-1,
global_search=SimulatedAnnealing(temperature=70, steps=50),
extend_variables=False)
def test():
images = make_training_images()
for descriptor in [None, Gaussian()]:
for global_search in [
None, SimulatedAnnealing(temperature=10, steps=5)
]:
for data_format in ['json', 'db']:
for save_memory in [
False,
]:
for fortran in [False, True]:
for cores in range(1, 4):
print(descriptor, global_search, data_format,
save_memory, fortran, cores)
pwd = os.getcwd()
testdir = 'read_write_test'
os.mkdir(testdir)
os.chdir(testdir)
regression = NeuralNetwork(hiddenlayers=(
5,
5,
))
calc = Amp(
label='calc',
descriptor=descriptor,
regression=regression,
fortran=fortran,
)
# Should start with new variables
calc.train(
images,
energy_goal=0.01,
force_goal=10.,
global_search=global_search,
extend_variables=True,
data_format=data_format,
save_memory=save_memory,
cores=cores,
)
# Test that we cannot overwrite. (Strange code
# here because we *want* it to raise an
# exception...)
try:
calc.train(
images,
energy_goal=0.01,
force_goal=10.,
global_search=global_search,
extend_variables=True,
data_format=data_format,
save_memory=save_memory,
cores=cores,
)
except IOError:
pass
else:
raise RuntimeError(
'Code allowed to overwrite!')
# Test that we can manually overwrite.
# Should start with existing variables
calc.train(
images,
energy_goal=0.01,
force_goal=10.,
global_search=global_search,
extend_variables=True,
data_format=data_format,
save_memory=save_memory,
overwrite=True,
cores=cores,
)
label = 'testdir'
if not os.path.exists(label):
os.mkdir(label)
# New directory calculator.
calc = Amp(
label='testdir/calc',
descriptor=descriptor,
regression=regression,
fortran=fortran,
)
# Should start with new variables
calc.train(
images,
energy_goal=0.01,
force_goal=10.,
global_search=global_search,
extend_variables=True,
data_format=data_format,
save_memory=save_memory,
cores=cores,
)
# Open existing, save under new name.
calc = Amp(
load='calc',
label='calc2',
descriptor=descriptor,
regression=regression,
fortran=fortran,
)
# Should start with existing variables
calc.train(
images,
energy_goal=0.01,
force_goal=10.,
global_search=global_search,
extend_variables=True,
data_format=data_format,
save_memory=save_memory,
cores=cores,
)
label = 'calc_new'
if not os.path.exists(label):
os.mkdir(label)
# Change label and re-train
calc.set_label('calc_new/calc')
# Should start with existing variables
calc.train(
images,
energy_goal=0.01,
force_goal=10.,
global_search=global_search,
extend_variables=True,
data_format=data_format,
save_memory=save_memory,
cores=cores,
)
# Open existing without specifying new name.
calc = Amp(
load='calc',
descriptor=descriptor,
regression=regression,
fortran=fortran,
)
# Should start with existing variables
calc.train(
images,
energy_goal=0.01,
force_goal=10.,
global_search=global_search,
extend_variables=True,
data_format=data_format,
save_memory=save_memory,
cores=cores,
)
os.chdir(pwd)
shutil.rmtree(testdir, ignore_errors=True)
del calc, regression
def test():
pwd = os.getcwd()
os.mkdir(os.path.join(pwd, 'consistnone'))
images = generate_images()
count = 0
for global_search in [None, 'SA']:
for fortran in [False, True]:
for extend_variables in [False, True]:
for data_format in ['db', 'json']:
for save_memory in [False]:
for cores in range(1, 7):
string = 'consistnone/%s-%s-%s-%s-%s-%i'
label = string % (global_search, fortran,
extend_variables, data_format,
save_memory, cores)
if global_search is 'SA':
global_search = \
SimulatedAnnealing(temperature=10, steps=5)
calc = Amp(descriptor=None,
regression=NeuralNetwork(
hiddenlayers=(2, 1),
activation='tanh',
weights=weights,
scalings=scalings,
),
fortran=fortran,
label=label)
calc.train(images=images,
energy_goal=10.**10.,
force_goal=10.**10.,
cores=cores,
data_format=data_format,
save_memory=save_memory,
global_search=global_search,
extend_variables=extend_variables)
if count == 0:
reference_cost_function = calc.cost_function
reference_energy_rmse = \
calc.energy_per_atom_rmse
reference_force_rmse = calc.force_rmse
ref_cost_fxn_variable_derivatives = \
calc.der_variables_cost_function
else:
assert (abs(calc.cost_function -
reference_cost_function) <
10.**(-10.)), \
'''Cost function value for %r fortran, %r
data format, %r save_memory, and %i cores is
not consistent with the value of python version
on single core.''' % (fortran, data_format,
save_memory, cores)
assert (abs(calc.energy_per_atom_rmse -
reference_energy_rmse) <
10.**(-10.)), \
'''Energy rmse value for %r fortran, %r data
format, %r save_memory, and %i cores is not
consistent with the value of python version on
single core.''' % (fortran, data_format,
save_memory, cores)
assert (abs(calc.force_rmse -
reference_force_rmse) < 10.**(-10.)), \
'''Force rmse value for %r fortran, %r data
format, %r save_memory, and %i cores is not
consistent with the value of python version on
single core.''' % (fortran, data_format,
save_memory, cores)
for _ in range(
len(ref_cost_fxn_variable_derivatives)):
assert (calc.der_variables_cost_function[_] -
ref_cost_fxn_variable_derivatives[_] <
10.**(-10.))
'''Derivative of the cost function for %r
fortran, %r data format, %r save_memory, and %i
cores is not consistent with the value of
python version on single
core. ''' % (fortran, data_format, save_memory,
cores)
count = count + 1