def train_images(images, HL, E_conv): Hidden_Layer=tuple(HL) calc = Amp(descriptor=Gaussian(), model=NeuralNetwork(hiddenlayers=Hidden_Layer)) calc.model.lossfunction = LossFunction(convergence={'energy_rmse': E_conv}) #calc.model.lossfunction = LossFunction(force_coefficient=-0.1) calc.train(images=images, overwrite=True)
from mlutils.neb import accelerate_neb from amp import Amp from amp.descriptor.gaussian import Gaussian from amp.model.neuralnetwork import NeuralNetwork from amp.model import LossFunction from ase.calculators.emt import EMT initial = 'initial.traj' final = 'final.traj' Gs = None n = 5 cutoff = 6.5 amp_calc = Amp(descriptor=Gaussian(cutoff=cutoff, fortran=True, Gs=Gs), model=NeuralNetwork(hiddenlayers=(n, n), fortran=True, checkpoints=None)) convergence = {'energy_rmse': 0.0001, 'force_rmse': 0.01} amp_calc.model.lossfunction = LossFunction(convergence=convergence) dft_calc = EMT() neb = accelerate_neb(initial=initial, final=final, tolerance=0.05, maxiter=200, fmax=0.05, ifmax=1., step=2., metric='fmax')
#!/usr/bin/python # mute from amp import Amp amp = Amp() amp.pwm.mute()
def train_rnn(baseframe=100, tframe=8, total_step=10, traj='ethane.traj', convergence={ 'energy_rmse': 0.25, 'force_rmse': 0.5 }, elements=['C', 'H', 'O'], hiddenlayers=(64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64), optim='ADAM', cores=4): """Gaussian/tflow train test.""" p = ple() label = 'amp' all_images = Trajectory(traj) nimg, mean_e = get_mean_energy(all_images) G = make_symmetry_functions(elements=elements, type='G2', etas=np.logspace(np.log10(0.05), np.log10(5.), num=4)) G += make_symmetry_functions(elements=elements, type='G5', etas=[0.005], zetas=[1., 4.], gammas=[+1., -1.]) G = {element: G for element in elements} # Gs=G if not isfile('amp.amp'): print('\nset up calculator ...\n') calc = Amp(descriptor=Gaussian(mode='atom-centered', Gs=G), model=NeuralNetwork(hiddenlayers=hiddenlayers, convergenceCriteria=convergence, activation='tanh', energy_coefficient=1.0, force_coefficient=None, optimizationMethod=optim, parameters={'energyMeanScale': mean_e}, maxTrainingEpochs=100000), label=label, cores=cores) # 'l-BFGS-b' or 'ADAM' trained_images = [all_images[j] for j in range(0, baseframe)] calc.train(overwrite=True, images=trained_images) del calc else: calc = Amp.load('amp.amp') calc.model.parameters['convergence'] = convergence calc.model.lossfunction = LossFunction(convergence=convergence) trained_images = [all_images[j] for j in range(0, baseframe)] calc.train(overwrite=True, images=trained_images) del calc tstep = int((nimg - baseframe) / tframe) if total_step > tstep: total_step = tstep print('Max train cycle of %d is allowed.' % total_step) edfts, eamps, eamps_ = [], [], [] dolabel = True basestep = int(baseframe / tframe) for step in range(basestep, total_step + basestep): new_images = [ all_images[j] for j in range(0 + step * tframe, tframe + step * tframe) ] trained_images.extend(new_images) x, edft, eamp, eamp_ = [], [], [], [] ii = step * tframe # ----- test ----- calc1 = Amp.load('amp.amp') for i, image in enumerate(new_images): x.append(ii) eamp_.append(calc1.get_potential_energy(image)) eamps_.append(eamp_[-1]) edft.append(image.get_potential_energy()) edfts.append(edft[-1]) ii += 1 del calc1 # ----- train ----- calc = Amp.load('amp.amp') calc.model.lossfunction = LossFunction(convergence=convergence) # calc.model.convergenceCriteria=convergence calc.train(overwrite=True, images=trained_images) del calc # ----- test ----- calc2 = Amp.load('amp.amp') print('\n---- current training result ---- \n') for i, image in enumerate(new_images): eamp.append(calc2.get_potential_energy(image)) eamps.append(eamp[-1]) print("energy(AMP) = %f energy(DFT) = %f" % (eamp[-1], edft[i])) # print("forces = %s" % str(calc2.get_forces(image))) del calc2 plot_energies(edfts, eamps, eamp_=None) system('epstopdf energies.eps') p.scatter(x, edft, eamp, eamp_, dolabel=dolabel) if dolabel: dolabel = False p.plot() system('epstopdf energies_scatter.eps')
# -*- coding: utf-8 -*- """ Created on Sun Apr 12 21:54:34 2020 @author: srava """ from ase.io import read from ase.io.trajectory import Trajectory import numpy as np from ase.calculators.emt import EMT from amp import Amp from amp.descriptor.gaussian import Gaussian from amp.utilities import hash_images from amp.model.neuralnetwork import NeuralNetwork import matplotlib.pyplot as plt calc = Amp(descriptor=Gaussian(), model=NeuralNetwork(), label='calc') calc.model.lossfunction.parameters['convergence'].update( {'energy_rmse': 0.05,}) calc.train(images='training_data.traj')
def test_calcs(): """Gaussian/Neural non-periodic standard. Checks that the answer matches that expected from previous Mathematica calculations. """ #: Making the list of non-periodic images images = [ Atoms( symbols="PdOPd2", pbc=np.array([False, False, False], dtype=bool), calculator=EMT(), cell=np.array([[1.0, 0.0, 0.0], [0.0, 1.0, 0.0], [0.0, 0.0, 1.0]]), positions=np.array([[0.0, 0.0, 0.0], [0.0, 2.0, 0.0], [0.0, 0.0, 3.0], [1.0, 0.0, 0.0]]), ), Atoms( symbols="PdOPd2", pbc=np.array([False, False, False], dtype=bool), calculator=EMT(), cell=np.array([[1.0, 0.0, 0.0], [0.0, 1.0, 0.0], [0.0, 0.0, 1.0]]), positions=np.array([[0.0, 1.0, 0.0], [1.0, 2.0, 1.0], [-1.0, 1.0, 2.0], [1.0, 3.0, 2.0]]), ), Atoms( symbols="PdO", pbc=np.array([False, False, False], dtype=bool), calculator=EMT(), cell=np.array([[1.0, 0.0, 0.0], [0.0, 1.0, 0.0], [0.0, 0.0, 1.0]]), positions=np.array([[2.0, 1.0, -1.0], [1.0, 2.0, 1.0]]), ), Atoms( symbols="Pd2O", pbc=np.array([False, False, False], dtype=bool), calculator=EMT(), cell=np.array([[1.0, 0.0, 0.0], [0.0, 1.0, 0.0], [0.0, 0.0, 1.0]]), positions=np.array([[-2.0, -1.0, -1.0], [1.0, 2.0, 1.0], [3.0, 4.0, 4.0]]), ), Atoms( symbols="Cu", pbc=np.array([False, False, False], dtype=bool), calculator=EMT(), cell=np.array([[1.0, 0.0, 0.0], [0.0, 1.0, 0.0], [0.0, 0.0, 1.0]]), positions=np.array([[0.0, 0.0, 0.0]]), ), ] # Parameters hiddenlayers = {"O": (2, ), "Pd": (2, ), "Cu": (2, )} Gs = {} Gs["G2_etas"] = [0.2] Gs["G2_rs_s"] = [0] Gs["G4_etas"] = [0.4] Gs["G4_zetas"] = [1] Gs["G4_gammas"] = [1] Gs["cutoff"] = 6.5 elements = ["O", "Pd", "Cu"] G = make_symmetry_functions(elements=elements, type="G2", etas=Gs["G2_etas"]) G += make_symmetry_functions( elements=elements, type="G4", etas=Gs["G4_etas"], zetas=Gs["G4_zetas"], gammas=Gs["G4_gammas"], ) amp_images = amp_hash(images) descriptor = Gaussian(Gs=G, cutoff=Gs["cutoff"]) descriptor.calculate_fingerprints(amp_images, calculate_derivatives=True) fingerprints_range = calculate_fingerprints_range(descriptor, amp_images) np.random.seed(1) O_weights_1 = np.random.rand(10, 2) O_weights_2 = np.random.rand(1, 3).reshape(-1, 1) np.random.seed(2) Pd_weights_1 = np.random.rand(10, 2) Pd_weights_2 = np.random.rand(1, 3).reshape(-1, 1) np.random.seed(3) Cu_weights_1 = np.random.rand(10, 2) Cu_weights_2 = np.random.rand(1, 3).reshape(-1, 1) weights = OrderedDict([ ("O", OrderedDict([(1, O_weights_1), (2, O_weights_2)])), ("Pd", OrderedDict([(1, Pd_weights_1), (2, Pd_weights_2)])), ("Cu", OrderedDict([(1, Cu_weights_1), (2, Cu_weights_2)])), ]) scalings = OrderedDict([ ("O", OrderedDict([("intercept", 0), ("slope", 1)])), ("Pd", OrderedDict([("intercept", 0), ("slope", 1)])), ("Cu", OrderedDict([("intercept", 0), ("slope", 1)])), ]) calc = Amp( descriptor, model=NeuralNetwork( hiddenlayers=hiddenlayers, weights=weights, scalings=scalings, activation="tanh", fprange=fingerprints_range, mode="atom-centered", fortran=False, ), logging=False, ) amp_energies = [calc.get_potential_energy(image) for image in images] amp_forces = [calc.get_forces(image) for image in images] amp_forces = np.concatenate(amp_forces) torch_O_weights_1 = torch.FloatTensor(O_weights_1[:-1, :]).t() torch_O_bias_1 = torch.FloatTensor(O_weights_1[-1, :]) torch_O_weights_2 = torch.FloatTensor(O_weights_2[:-1, :]).t() torch_O_bias_2 = torch.FloatTensor(O_weights_2[-1, :]) torch_Pd_weights_1 = torch.FloatTensor(Pd_weights_1[:-1, :]).t() torch_Pd_bias_1 = torch.FloatTensor(Pd_weights_1[-1, :]) torch_Pd_weights_2 = torch.FloatTensor(Pd_weights_2[:-1, :]).t() torch_Pd_bias_2 = torch.FloatTensor(Pd_weights_2[-1, :]) torch_Cu_weights_1 = torch.FloatTensor(Cu_weights_1[:-1, :]).t() torch_Cu_bias_1 = torch.FloatTensor(Cu_weights_1[-1, :]) torch_Cu_weights_2 = torch.FloatTensor(Cu_weights_2[:-1, :]).t() torch_Cu_bias_2 = torch.FloatTensor(Cu_weights_2[-1, :]) device = "cpu" dataset = AtomsDataset( images, descriptor=Gaussian, cores=1, label="consistency", Gs=Gs, forcetraining=True, ) fp_length = dataset.fp_length batch_size = len(dataset) dataloader = DataLoader(dataset, batch_size, collate_fn=collate_amp, shuffle=False) model = FullNN(elements, [fp_length, 2, 2], device, forcetraining=True) model.state_dict()["elementwise_models.O.model_net.0.weight"].copy_( torch_O_weights_1) model.state_dict()["elementwise_models.O.model_net.0.bias"].copy_( torch_O_bias_1) model.state_dict()["elementwise_models.O.model_net.2.weight"].copy_( torch_O_weights_2) model.state_dict()["elementwise_models.O.model_net.2.bias"].copy_( torch_O_bias_2) model.state_dict()["elementwise_models.Pd.model_net.0.weight"].copy_( torch_Pd_weights_1) model.state_dict()["elementwise_models.Pd.model_net.0.bias"].copy_( torch_Pd_bias_1) model.state_dict()["elementwise_models.Pd.model_net.2.weight"].copy_( torch_Pd_weights_2) model.state_dict()["elementwise_models.Pd.model_net.2.bias"].copy_( torch_Pd_bias_2) model.state_dict()["elementwise_models.Cu.model_net.0.weight"].copy_( torch_Cu_weights_1) model.state_dict()["elementwise_models.Cu.model_net.0.bias"].copy_( torch_Cu_bias_1) model.state_dict()["elementwise_models.Cu.model_net.2.weight"].copy_( torch_Cu_weights_2) model.state_dict()["elementwise_models.Cu.model_net.2.bias"].copy_( torch_Cu_bias_2) import torch.nn as nn for name, layer in model.named_modules(): if isinstance(layer, MLP): layer.model_net = nn.Sequential(layer.model_net, Tanh()) for batch in dataloader: x = to_tensor(batch[0], device) y = to_tensor(batch[1], device) energy_pred, force_pred = model(x) for idx, i in enumerate(amp_energies): assert round(i, 4) == round( energy_pred.tolist()[idx][0], 4), "The predicted energy of image %i is wrong!" % (idx + 1) print("Energy predictions are correct!") for idx, sample in enumerate(amp_forces): for idx_d, value in enumerate(sample): predict = force_pred.tolist()[idx][idx_d] assert abs(value - predict) < 0.0001, ( "The predicted force of image % i, direction % i is wrong! Values: %s vs %s" % (idx + 1, idx_d, value, force_pred.tolist()[idx][idx_d])) print("Force predictions are correct!")
def train_images(images): calc = Amp(descriptor=Gaussian(), model=NeuralNetwork(hiddenlayers=(10, 10, 10))) calc.model.lossfunction = LossFunction(convergence={'energy_rmse': 0.001}) calc.model.lossfunction = LossFunction(force_coefficient=-0.1) calc.train(images=images, overwrite=True)
#!/usr/bin/env python from amp import Amp from amp.descriptor import * from amp.regression import * calc = Amp(label="./", descriptor=Behler(cutoff=6.0), regression=NeuralNetwork(hiddenlayers=(2, 3))) calc.train( "../train.db", # The training data cores=1, global_search=None, # not found the simulated annealing feature useful extend_variables=False) # feature does not work properly and will crash
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
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
images = [atoms] g2_etas = [0.005] g2_rs_s = [0] * 4 g4_etas = [0.005] g4_zetas = [1., 4.] g4_gammas = [1., -1.] cutoff = 4 make_amp_descriptors_simple_nn(images, g2_etas, g2_rs_s, g4_etas, g4_zetas, g4_gammas, cutoff) G = make_symmetry_functions(elements=elements, type='G2', etas=g2_etas) #Add Rs parameter (0.0 for default) to comply with my version of AMP #for g in G: # g['Rs'] = 0.0 G += make_symmetry_functions(elements=elements, type='G4', etas=g4_etas, zetas=g4_zetas, gammas=g4_gammas) calc = Amp(descriptor=Gaussian(Gs=G, cutoff=4.), cores=ncores, model=NeuralNetwork(hiddenlayers=hiddenlayers)) calc.model.lossfunction = LossFunction(convergence=convergence, force_coefficient=0.001) calc.train(images=images)
#import os #from ase import Atoms, Atom, units #import ase.io from amp import Amp from amp.descriptor.gaussian import Gaussian from amp.model.neuralnetwork import NeuralNetwork from amp.model import LossFunction calc = Amp(descriptor=Gaussian(), model=NeuralNetwork(hiddenlayers=(10, 10, 10))) calc.model.lossfunction = LossFunction(convergence={ 'energy_rmse': 0.02, 'force_rmse': 0.03 }) calc.train(images='geoopt_LCAO.traj')
def train_amp(baseframe=200, traj='ethane.traj', convergence={ 'energy_rmse': 0.25, 'force_rmse': 0.5 }, elements=['C', 'H', 'O'], cores=4): """Gaussian/tflow train test.""" p = ple() label = 'amp' all_images = Trajectory(traj) nimg, mean_e = get_mean_energy(all_images) G = make_symmetry_functions(elements=elements, type='G2', etas=np.logspace(np.log10(0.05), np.log10(5.), num=4)) G += make_symmetry_functions(elements=elements, type='G5', etas=[0.005], zetas=[1., 4.], gammas=[+1., -1.]) G = {element: G for element in elements} # Gs=G if not isfile('amp.amp'): # print('\nset up calculator ...\n') calc = Amp(descriptor=Gaussian(mode='atom-centered', Gs=G), model=NeuralNetwork(hiddenlayers=(1024, 1024, 1024, 512, 512, 256, 256, 256, 256, 128, 128), convergenceCriteria=convergence, activation='tanh', energy_coefficient=1.0, force_coefficient=None, optimizationMethod='ADAM', parameters={'energyMeanScale': mean_e}, maxTrainingEpochs=100000), label=label, cores=cores) # 'l-BFGS-b' or 'ADAM' trained_images = [all_images[j] for j in range(0, baseframe)] calc.train(overwrite=True, images=trained_images) del calc else: calc = Amp.load('amp.amp') calc.model.parameters['convergence'] = convergence calc.model.lossfunction = LossFunction(convergence=convergence) trained_images = [all_images[j] for j in range(0, baseframe)] calc.train(overwrite=True, images=trained_images) del calc edfts, eamps, eamps_ = [], [], [] dolabel = True basestep = int(baseframe / tframe) system('epstopdf energies.eps') p.scatter(x, edft, eamp, eamp_, dolabel=dolabel) p.plot() plot_energies(edfts, eamps, eamp_=eamps_) system('epstopdf energies_scatter.eps')
def periodic_test(): """Gaussian/tflowNeural periodic.""" perform, reason = check_perform() if not perform: print('Skipping this test because {}'.format(reason)) return from amp.model.tflow import NeuralNetwork # Making the list of periodic 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.]]))] # Correct energies and forces correct_energies = [3.8560954326995978, 1.6120748520627273, 0.19433107801410093] correct_forces = \ [[[0.14747720528015523, -3.3010645563584973, 3.3008168318984463], [0.03333579762326405, 9.050780376599887, -0.42608278400777605], [-0.1808130029034193, -5.7497158202413905, -2.8747340478906698]], [[6.5035267996045045 * (10.**(-6.)), -6.503526799604495 * (10.**(-6.)), 0.00010834689201069249], [-6.5035267996045045 * (10.**(-6.)), 6.503526799604495 * (10.**(-6.)), -0.00010834689201069249]], [[0.0, 0.0, 0.0]]] # 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, 1), 'Pd': (2, 1), 'Cu': (2, 1)} 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)]))]) fingerprints_range = {"Cu": np.array([[2.8636310860653253, 2.8636310860653253], [1.5435994865298275, 1.5435994865298275]]), "O": np.array([[2.9409056366723028, 2.972494902604392], [1.9522542722823606, 4.0720361595017245]]), "Pd": np.array([[2.4629488092411096, 2.6160138774087125], [0.27127576524253594, 0.5898312261433813]])} # Testing pure-python and fortran versions of Gaussian-neural force call for fortran in [False, True]: for cores in range(1, 4): label = 'call-periodic/%s-%i' % (fortran, cores) calc = Amp(descriptor=Gaussian(cutoff=4., Gs=Gs, fortran=fortran), model=NeuralNetwork(hiddenlayers=hiddenlayers, weights=weights, scalings=scalings, activation='tanh', fprange=fingerprints_range, unit_type="double"), label=label, dblabel=label, cores=cores) predicted_energies = [calc.get_potential_energy(image) for image in images] for image_no in range(len(predicted_energies)): print(predicted_energies[image_no]) print(correct_energies[image_no]) diff = abs(predicted_energies[image_no] - correct_energies[image_no]) assert (diff < 10.**(-14.)), \ 'The predicted energy of image %i is wrong!' % ( image_no + 1) predicted_forces = [calc.get_forces(image) for image in images] for image_no in range(len(predicted_forces)): print('predicted forces:') print(predicted_forces[image_no]) print('correct forces:') print(np.array(correct_forces[image_no])) for index in range(np.shape(predicted_forces[image_no])[0]): for direction in range( np.shape(predicted_forces[image_no])[1]): diff = abs(predicted_forces[image_no][index][ direction] - correct_forces[image_no][index][direction]) assert (diff < 10.**(-11.)), \ 'The predicted %i force of atom %i of image' \ ' %i is wrong!' % (direction, index, image_no + 1)
def test(): ########################################################################### # Parameters weights = \ OrderedDict([(1, np.array([[0.14563579, 0.19176385], [-0.01991609, 0.35873379], [-0.27988951, 0.03490866], [0.19195185, 0.43116313], [0.41035737, 0.02617128], [-0.13235187, -0.23112657], [-0.29065111, 0.23865951], [0.05854897, 0.24249052], [0.13660673, 0.19288898], [0.31894165, -0.41831075], [-0.23522261, -0.24009372], [-0.14450575, -0.15275409], [0., 0.]])), (2, np.array([[-0.27415999], [0.28538579], [0.]])), (3, np.array([[0.32147131], [0.]]))]) scalings = OrderedDict([('intercept', 3.), ('slope', 2.)]) images = generate_images() ########################################################################### # Testing pure-python and fortran versions of CartesianNeural on different # number of processes for fortran in [False, True]: calc = Amp( descriptor=None, regression=NeuralNetwork(hiddenlayers=(2, 1), weights=weights, scalings=scalings, activation='tanh'), fortran=fortran, ) predicted_energies = [ calc.get_potential_energy(image) for image in images ] for image_no in range(len(predicted_energies)): assert (abs(predicted_energies[image_no] - correct_predicted_energies[image_no]) < 5 * 10.**(-10.)), \ 'The calculated energy of image %i is wrong!' % (image_no + 1) predicted_forces = [calc.get_forces(image) for image in images] for image_no in range(len(predicted_forces)): for index in range(np.shape(predicted_forces[image_no])[0]): for direction in range(3): assert (abs(predicted_forces[image_no][index][direction] - correct_predicted_forces[image_no][index] [direction]) < 5 * 10.**(-10.)), \ 'The calculated %i force of atom %i of image %i is' \ 'wrong!' % (direction, index, image_no + 1)
def non_periodic_test(): """Gaussian/tflowNeural non-periodic.""" perform, reason = check_perform() if not perform: print('Skipping this test because {}'.format(reason)) return from amp.model.tflow import NeuralNetwork # Making the list of non-periodic images 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.]]))] # Correct energies and forces correct_energies = [14.231186811226152, 14.327219917287948, 5.5742510565528285, 9.41456771216968, -0.5019297954597407] correct_forces = \ [[[-0.05095024246182649, -0.10709193432146558, -0.09734321482638622], [-0.044550772904033635, 0.2469763195486647, -0.07617425912869778], [-0.02352490951707703, -0.050782839419131864, 0.24409220250631508], [0.11902592488293715, -0.08910154580806727, -0.07057472855123109]], [[-0.024868720575099375, -0.07417891957113862, -0.12121240797223251], [0.060156158438252574, 0.017517013378773042, -0.020047135079325505], [-0.10901144291312388, -0.06671262448352767, 0.06581556263014315], [0.07372400504997068, 0.12337453067589325, 0.07544398042141486]], [[0.10151747265164626, -0.10151747265164626, -0.20303494530329252], [-0.10151747265164626, 0.10151747265164626, 0.20303494530329252]], [[-0.00031177673224312745, -0.00031177673224312745, -0.0002078511548287517], [0.004823209772264884, 0.004823209772264884, 0.006975000714861393], [-0.004511433040021756, -0.004511433040021756, -0.006767149560032641]], [[0.0, 0.0, 0.0]]] # 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, 1), 'Pd': (2, 1), 'Cu': (2, 1)} 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)]))]) fingerprints_range = {"Cu": np.array([[0.0, 0.0], [0.0, 0.0], [0.0, 0.0]]), "O": np.array([[0.2139617720858539, 2.258090276328769], [0.0, 1.085656080548734], [0.0, 0.0]]), "Pd": np.array([[0.0, 1.4751761770313006], [0.0, 0.28464992134267897], [0.0, 0.20167521020630502]])} # Testing pure-python and fortran versions of Gaussian-neural force call for fortran in [False, True]: for cores in range(1, 6): label = 'call-nonperiodic/%s-%i' % (fortran, cores) calc = Amp(descriptor=Gaussian(cutoff=6.5, Gs=Gs, fortran=fortran), model=NeuralNetwork(hiddenlayers=hiddenlayers, weights=weights, scalings=scalings, activation='sigmoid', fprange=fingerprints_range), label=label, dblabel=label, cores=cores) predicted_energies = [calc.get_potential_energy(image) for image in images] for image_no in range(len(predicted_energies)): print(predicted_energies[image_no]) print(correct_energies[image_no]) diff = abs(predicted_energies[image_no] - correct_energies[image_no]) assert (diff < 10.**(-3.)), \ 'The predicted energy of image %i is wrong!' % ( image_no + 1) predicted_forces = [calc.get_forces(image) for image in images] for image_no in range(len(predicted_forces)): print('predicted forces:') print(predicted_forces[image_no]) print('correct forces:') print(np.array(correct_forces[image_no])) for index in range(np.shape(predicted_forces[image_no])[0]): for direction in range( np.shape(predicted_forces[image_no])[1]): diff = abs(predicted_forces[image_no][index][ direction] - correct_forces[image_no][index][direction]) assert (diff < 10.**(-3.)), \ 'The predicted %i force of atom %i of image %i ' \ 'is wrong!' % (direction, index, image_no + 1)
{"type":"G2", "element":"Pd", "eta":400., "Rs":4.0}, {"type":"G2", "element":"Pd", "eta":400., "Rs":5.0}, {"type":"G2", "element":"Pd", "eta":400., "Rs":6.0}, {"type":"G4", "elements":["Pd", "Pd"],"eta":0.005, "gamma":-1.0, "zeta":100.0, "theta_s":-1.0}, {"type":"G4", "elements":["Pd", "Pd"],"eta":0.005, "gamma":-1.0, "zeta":100.0, "theta_s":-1.5}, {"type":"G4", "elements":["Pd", "Pd"],"eta":0.005, "gamma":-1.0, "zeta":100.0, "theta_s":-1.75}, {"type":"G4", "elements":["Pd", "Pd"],"eta":0.005, "gamma":-1.0, "zeta":100.0, "theta_s":-2.0}, {"type":"G4", "elements":["Pd", "Pd"],"eta":0.005, "gamma":-1.0, "zeta":300.0, "theta_s":-2.15}, {"type":"G4", "elements":["Pd", "Pd"],"eta":0.005, "gamma":-1.0, "zeta":300.0, "theta_s":-2.25}, {"type":"G4", "elements":["Pd", "Pd"],"eta":0.005, "gamma":1.0, "zeta":160.0, "theta_s":0.0}, {"type":"G4", "elements":["Pd", "Pd"],"eta":0.005, "gamma":1.0, "zeta":320.0, "theta_s":0.25}, {"type":"G4", "elements":["Pd", "Pd"],"eta":0.005, "gamma":1.0, "zeta":640.0, "theta_s":0.35}, {"type":"G4", "elements":["Pd", "Pd"],"eta":0.005, "gamma":1.0, "zeta":160.0, "theta_s":0.5}, {"type":"G4", "elements":["Pd", "Pd"],"eta":0.005, "gamma":1.0, "zeta":160.0, "theta_s":0.75}, ]} calc = Amp(descriptor=Gaussian(Gs=Gs, cutoff=Cosine(6.0) ), cores=24, model=NeuralNetwork(hiddenlayers=(50,), activation='sigmoid', maxTrainingEpochs=20000, energy_coefficient=1.0, force_coefficient=0.1, optimizationMethod='l-BFGS-b', convergenceCriteria={'energy_rmse': 0.05, 'force_rmse': 0.05})) calc.train(images='train.traj',overwrite=True)
def test(): """Displaced atom test.""" ########################################################################### # Parameters atoms = 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.]])) ########################################################################### # 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 }] } hiddenlayers = {'O': (2, ), 'Pd': (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]]))])) ]) scalings = OrderedDict([ ('O', OrderedDict([('intercept', -2.3), ('slope', 4.5)])), ('Pd', OrderedDict([('intercept', 1.6), ('slope', 2.5)])) ]) fingerprints_range = { "O": np.array([[0.21396177208585404, 2.258090276328769], [0.0, 2.1579067008202975], [0.0, 0.0]]), "Pd": np.array([[0.0, 1.4751761770313006], [0.0, 0.697686078889583], [0.0, 0.37848964715610417]]) } ########################################################################### calc = Amp(descriptor=Gaussian( cutoff=6.5, Gs=Gs, fortran=False, ), model=NeuralNetwork(hiddenlayers=hiddenlayers, weights=weights, scalings=scalings, fprange=fingerprints_range, mode='atom-centered'), cores=1) atoms.set_calculator(calc) e1 = atoms.get_potential_energy(apply_constraint=False) e2 = calc.get_potential_energy(atoms) f1 = atoms.get_forces(apply_constraint=False) atoms[0].x += 0.5 boolean = atoms.calc.calculation_required(atoms, properties=['energy']) e3 = atoms.get_potential_energy(apply_constraint=False) e4 = calc.get_potential_energy(atoms) f2 = atoms.get_forces(apply_constraint=False) assert (e1 == e2 and e3 == e4 and abs(e1 - e3) > 10.**(-3.) and (boolean is True) and (not (f1 == f2).all())), 'Displaced-atom test broken!'
def test(): pwd = os.getcwd() os.mkdir(os.path.join(pwd, 'rotation_test')) for descriptor in [Gaussian(), Bispectrum(jmax=2.), Zernike(nmax=5)]: pwd = os.getcwd() os.mkdir(os.path.join(pwd, 'rotation_test/before_rot')) os.mkdir(os.path.join(pwd, 'rotation_test/after_rot')) # Non-rotated atomic configuration atoms = Atoms([ Atom('Pt', (0., 0., 0.)), Atom('Pt', (0., 0., 1.)), Atom('Pt', (0., 2., 1.)) ]) atoms.set_constraint(FixAtoms(indices=[0])) atoms.set_calculator(EMT()) atoms.get_potential_energy() atoms.get_forces(apply_constraint=False) calc = Amp(descriptor=descriptor, fortran=False, label='rotation_test/before_rot/') calc.train(images=[atoms], force_goal=None, energy_goal=10.**10., extend_variables=False, global_search=None, data_format='json') ########################################################################### # Randomly Rotated (and translated) atomic configuration rot = [random.random(), random.random(), random.random()] for i in range(1, len(atoms)): (atoms[i].x, atoms[i].y, atoms[i].z) = rotate_atom(atoms[i].x, atoms[i].y, atoms[i].z, rot[0] * np.pi, rot[1] * np.pi, rot[2] * np.pi) disp = [random.random(), random.random(), random.random()] for atom in atoms: atom.x += disp[0] atom.y += disp[1] atom.z += disp[2] calc = Amp(descriptor=descriptor, fortran=False, label='rotation_test/after_rot/') calc.train(images=[atoms], force_goal=None, energy_goal=10.**10., extend_variables=False, global_search=None, data_format='json') ########################################################################### fp1 = paropen('rotation_test/before_rot/fingerprints.json', 'rb') nonrotated_data = json.load(fp1) fp2 = paropen('rotation_test/after_rot/fingerprints.json', 'rb') rotated_data = json.load(fp2) for hash1, hash2 in zip(nonrotated_data.keys(), rotated_data.keys()): for index in nonrotated_data[hash1]: for _ in range(len(nonrotated_data[hash1][index])): assert abs(nonrotated_data[hash1][index][_] - rotated_data[hash2][index][_]) < 10.**(-7.) shutil.rmtree('rotation_test/before_rot') shutil.rmtree('rotation_test/after_rot')
def test(): """Guassian/Neural training. Checks consistency of pure-python and fortran versions. """ images = make_images() convergence = {'energy_rmse': 10.**10., 'energy_maxresid': 10.**10., 'force_rmse': 10.**10., 'force_maxresid': 10.**10., } regressor = Regressor(optimizer='BFGS') count = 0 for fortran in [False, True]: for cores in range(1, 2): string = 'consistgauss/%s-%i' label = string % (fortran, cores) calc = Amp(descriptor=Gaussian(cutoff=cutoff, Gs=Gs, fortran=fortran,), model=NeuralNetwork(hiddenlayers=hiddenlayers, weights=weights, scalings=scalings, activation=activation, fprange=fingerprints_range, regressor=regressor,), label=label, cores=1) lossfunction = LossFunction(convergence=convergence) calc.model.lossfunction = lossfunction calc.train(images=images,) if count == 0: ref_loss = calc.model.lossfunction.loss ref_energy_loss = calc.model.lossfunction.energy_loss ref_force_loss = calc.model.lossfunction.force_loss ref_dloss_dparameters = \ calc.model.lossfunction.dloss_dparameters else: assert (abs(calc.model.lossfunction.loss - ref_loss) < 10.**(-10.)), \ '''Loss function value for %r fortran, and %i cores is not consistent with the value of python version on single core.''' % (fortran, cores) assert (abs(calc.model.lossfunction.energy_loss - ref_energy_loss) < 10.**(-9.)), \ '''Energy rmse value for %r fortran, and %i cores is not consistent with the value of python version on single core.''' % (fortran, cores) assert (abs(calc.model.lossfunction.force_loss - ref_force_loss) < 10.**(-9.)), \ '''Force rmse value for %r fortran, and %i cores is not consistent with the value of python version on single core.''' % (fortran, cores) for _ in range(len(ref_dloss_dparameters)): assert (calc.model.lossfunction.dloss_dparameters[_] - ref_dloss_dparameters[_] < 10.**(-10.)) '''Derivative of the cost function for %r fortran, and %i cores is not consistent with the value of python version on single core. ''' % (fortran, cores) count = count + 1
def periodic_0th_bfgs_step_test(): """Gaussian/Neural training periodic standard test. Compares results to that expected from separate mathematica calculations. """ # 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 if aseversion < 12: # EMT values have changed from 3.12.0 version ref_loss = 8004.292841411172 ref_energyloss = (43.7360019403031**2.) * 3 ref_forceloss = (137.40994760947325**2.) * 3 ref_dloss_dparameters = np.array([ 0.08141668748130322, 0.03231235582925534, 0.04388650395738586, 0.017417514465922313, 0.028431276597563077, 0.011283700608814465, 0.0941695726576061, -0.12322258890990219, 0.12679918754154568, 63.53960075374332, 0.01624770019548904, -86.6263955859162, -0.01777752828707744, 86.22415217526024, 0.017745913074496918, 104.58358033298292, -96.73280209888215, -99.09843648905876, -8.302880631972338, -1.2590007162074357, 8.302877346883133, 1.25875988418134, -8.302866610678247, -1.2563833805675353, 28.324298392680998, 28.093155094726413, -29.37874455931869, -11.247473567044866, 11.119951466664787, -87.08582317481387, -20.939485239182346, -125.73267675705365, -35.138524407482116 ]) else: ref_loss = 8004.287750978173 ref_energyloss = (43.73598563177581**2.) * 3 ref_forceloss = (137.409923023214**2.) * 3 ref_dloss_dparameters = np.array([ 0.08141663280688925, 0.03231233413027478, 0.043886474485922956, 0.01741750276939638, 0.02843125750487539, 0.011283693031378718, 0.09416950941914284, -0.12322250616122936, 0.1267991023910503, 63.53958764057119, 0.016247696749304368, -86.62637753054923, -0.01777752451341436, 86.22413420485914, 0.01774590930723711, 104.58353326982777, -96.73275667196937, -99.09839026204304, -8.302877823431269, -1.2590002903842232, 8.302874538343092, 1.2587594584335775, -8.302863802141216, -1.2563829555383859, 28.32428881173613, 28.093145591893936, -29.37873462156934, -11.24746601393696, 11.11994399919284, -87.08579155328007, -20.93947792122797, -125.73262989900473, -35.13850819392253 ]) # Testing pure-python and fortran versions of Gaussian-neural on different # number of processes for fortran in [False, True]: for cores in range(1, 4): label = 'train-periodic/%s-%i' % (fortran, cores) print(label) calc = Amp(descriptor=Gaussian( cutoff=4., Gs=Gs, fortran=fortran, ), model=NeuralNetwork( hiddenlayers=hiddenlayers, weights=weights, scalings=scalings, activation='tanh', regressor=regressor, fortran=fortran, ), label=label, dblabel=label, cores=cores) lossfunction = LossFunction(convergence=convergence) calc.model.lossfunction = lossfunction calc.train(images=images, ) diff = abs(calc.model.lossfunction.loss - ref_loss) print("diff at 414 =", diff) assert (diff < 10.**(-10.)), \ 'Calculated value of loss function is wrong!' diff = abs(calc.model.lossfunction.energy_loss - ref_energyloss) assert (diff < 10.**(-10.)), \ 'Calculated value of energy per atom RMSE is wrong!' diff = abs(calc.model.lossfunction.force_loss - ref_forceloss) assert (diff < 10 ** (-9.)), \ 'Calculated value of force RMSE is wrong!' for _ in range(len(ref_dloss_dparameters)): diff = abs(calc.model.lossfunction.dloss_dparameters[_] - ref_dloss_dparameters[_]) assert(diff < 10 ** (-10.)), \ 'Calculated value of loss function derivative is wrong!' dblabel = label secondlabel = '_' + label calc = Amp(descriptor=Gaussian(cutoff=4., Gs=Gs, fortran=fortran), model=NeuralNetwork( hiddenlayers=hiddenlayers, weights=weights, scalings=scalings, activation='tanh', regressor=regressor, fortran=fortran, ), label=secondlabel, dblabel=dblabel, cores=cores) lossfunction = LossFunction(convergence=convergence) calc.model.lossfunction = lossfunction calc.train(images=images, ) diff = abs(calc.model.lossfunction.loss - ref_loss) assert (diff < 10.**(-10.)), \ 'Calculated value of loss function is wrong!' diff = abs(calc.model.lossfunction.energy_loss - ref_energyloss) assert (diff < 10.**(-10.)), \ 'Calculated value of energy per atom RMSE is wrong!' diff = abs(calc.model.lossfunction.force_loss - ref_forceloss) assert (diff < 10 ** (-9.)), \ 'Calculated value of force RMSE is wrong!' for _ in range(len(ref_dloss_dparameters)): diff = abs(calc.model.lossfunction.dloss_dparameters[_] - ref_dloss_dparameters[_]) assert(diff < 10 ** (-10.)), \ 'Calculated value of loss function derivative is wrong!'
def test_calcs(): """Gaussian/Neural non-periodic standard. Checks that the answer matches that expected from previous Mathematica calculations. """ #: Making the list of non-periodic images images = [ Atoms( symbols="PdOPd2", pbc=np.array([False, False, False], dtype=bool), calculator=EMT(), cell=np.array([[1.0, 0.0, 0.0], [0.0, 1.0, 0.0], [0.0, 0.0, 1.0]]), positions=np.array([[0.0, 0.0, 0.0], [0.0, 2.0, 0.0], [0.0, 0.0, 3.0], [1.0, 0.0, 0.0]]), ), Atoms( symbols="PdOPd2", pbc=np.array([False, False, False], dtype=bool), calculator=EMT(), cell=np.array([[1.0, 0.0, 0.0], [0.0, 1.0, 0.0], [0.0, 0.0, 1.0]]), positions=np.array([[0.0, 1.0, 0.0], [1.0, 2.0, 1.0], [-1.0, 1.0, 2.0], [1.0, 3.0, 2.0]]), ), Atoms( symbols="PdO", pbc=np.array([False, False, False], dtype=bool), calculator=EMT(), cell=np.array([[1.0, 0.0, 0.0], [0.0, 1.0, 0.0], [0.0, 0.0, 1.0]]), positions=np.array([[2.0, 1.0, -1.0], [1.0, 2.0, 1.0]]), ), Atoms( symbols="Pd2O", pbc=np.array([False, False, False], dtype=bool), calculator=EMT(), cell=np.array([[1.0, 0.0, 0.0], [0.0, 1.0, 0.0], [0.0, 0.0, 1.0]]), positions=np.array([[-2.0, -1.0, -1.0], [1.0, 2.0, 1.0], [3.0, 4.0, 4.0]]), ), Atoms( symbols="Cu", pbc=np.array([False, False, False], dtype=bool), calculator=EMT(), cell=np.array([[1.0, 0.0, 0.0], [0.0, 1.0, 0.0], [0.0, 0.0, 1.0]]), positions=np.array([[0.0, 0.0, 0.0]]), ), ] [a.get_potential_energy() for a in images] # Parameters hiddenlayers = {"O": (2, ), "Pd": (2, ), "Cu": (2, )} Gs = {} Gs["G2_etas"] = [0.2] Gs["G2_rs_s"] = [0] Gs["G4_etas"] = [0.4] Gs["G4_zetas"] = [1] Gs["G4_gammas"] = [1] Gs["cutoff"] = 6.5 elements = ["O", "Pd", "Cu"] G = make_symmetry_functions(elements=elements, type="G2", etas=Gs["G2_etas"]) G += make_symmetry_functions( elements=elements, type="G4", etas=Gs["G4_etas"], zetas=Gs["G4_zetas"], gammas=Gs["G4_gammas"], ) hashed_images = hash_images(images, Gs) descriptor = Gaussian(Gs=G, cutoff=Gs["cutoff"]) descriptor.calculate_fingerprints(hashed_images, calculate_derivatives=True) fingerprints_range = calculate_fingerprints_range(descriptor, hashed_images) weights = OrderedDict([ ( "O", OrderedDict([ ( 1, np.array([ [0.5, 0.5], [0.5, 0.5], [0.5, 0.5], [0.5, 0.5], [0.5, 0.5], [0.5, 0.5], [0.5, 0.5], [0.5, 0.5], [0.5, 0.5], [0.5, 0.5], ]), ), (2, np.matrix([[0.5], [0.5], [0.5]])), ]), ), ( "Pd", OrderedDict([ ( 1, np.array([ [0.5, 0.5], [0.5, 0.5], [0.5, 0.5], [0.5, 0.5], [0.5, 0.5], [0.5, 0.5], [0.5, 0.5], [0.5, 0.5], [0.5, 0.5], [0.5, 0.5], ]), ), (2, np.array([[0.5], [0.5], [0.5]])), ]), ), ( "Cu", OrderedDict([ ( 1, np.array([ [0.5, 0.5], [0.5, 0.5], [0.5, 0.5], [0.5, 0.5], [0.5, 0.5], [0.5, 0.5], [0.5, 0.5], [0.5, 0.5], [0.5, 0.5], [0.5, 0.5], ]), ), (2, np.array([[0.5], [0.5], [0.5]])), ]), ), ]) scalings = OrderedDict([ ("O", OrderedDict([("intercept", 0), ("slope", 1)])), ("Pd", OrderedDict([("intercept", 0), ("slope", 1)])), ("Cu", OrderedDict([("intercept", 0), ("slope", 1)])), ]) calc = Amp( descriptor, model=NeuralNetwork( hiddenlayers=hiddenlayers, weights=weights, scalings=scalings, activation="linear", fprange=fingerprints_range, mode="atom-centered", fortran=False, ), logging=False, ) amp_energies = [calc.get_potential_energy(image) for image in images] amp_forces = [calc.get_forces(image) for image in images] amp_forces = np.concatenate(amp_forces) device = "cpu" dataset = AtomsDataset(images, descriptor=DummyGaussian, cores=1, label='test', Gs=Gs, forcetraining=True) fp_length = dataset.fp_length batch_size = len(dataset) dataloader = DataLoader(dataset, batch_size, collate_fn=collate_amp, shuffle=False) model = FullNN(elements, [fp_length, 2, 2], device, forcetraining=True) for name, layer in model.named_modules(): if isinstance(layer, Dense): layer.activation = None init.constant_(layer.weight, 0.5) init.constant_(layer.bias, 0.5) for batch in dataloader: input_data = [batch[0], len(batch[1]), batch[3]] for element in elements: input_data[0][element][0] = ( input_data[0][element][0].to(device).requires_grad_(True)) fp_primes = batch[4] energy_pred, force_pred = model(input_data, fp_primes) for idx, i in enumerate(amp_energies): assert round(i, 4) == round( energy_pred.tolist()[idx][0], 4), "The predicted energy of image %i is wrong!" % (idx + 1) print("Energy predictions are correct!") for idx, sample in enumerate(amp_forces): for idx_d, value in enumerate(sample): predict = force_pred.tolist()[idx][idx_d] assert abs(value - predict) < 0.00001, ( "The predicted force of image % i, direction % i is wrong! Values: %s vs %s" % (idx + 1, idx_d, value, force_pred.tolist()[idx][idx_d])) print("Force predictions are correct!")
def non_periodic_0th_bfgs_step_test(): """Gaussian/Neural training non-periodic standard test. Compares results to that expected from separate mathematica calculations. """ 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 if aseversion < 12: # EMT values have changed from 3.12.0 version ref_loss = 7144.8107853579895 ref_energyloss = (24.318837496016506**2.) * 5 ref_forceloss = (144.70282477494519**2.) * 5 ref_dloss_dparameters = np.array([ 0, 0, 0, 0, 0, 0, 0.01374139170953901, 0.36318423812749656, 0.028312691567496464, 0.6012336354445753, 0.9659002689921986, -1.289777005924742, -0.5718960934643078, -2.642566722179569, -1.196039924610482, 0, 0, -2.72563797131018, -0.9080181024866707, -0.7739948323226851, -0.29157894253717415, -2.0599829042717404, -0.6156374289895887, -0.006086517460749253, -0.829678548408266, 0.0008092646745710161, 0.04161302703491613, 0.0034264690790135606, -0.957800456897051, -0.006281929606579444, -0.2883588477371198, -4.245777410962108, -4.3174120941045535, -8.02385959091948, -3.240512651984099, -27.289862194988853, -26.8177742762544, -82.45107056051073, -80.68167683508715 ]) ref_energy_maxresid = 54.21915548269209 ref_force_maxresid = 791.6736436232306 else: ref_loss = 7144.807220773296 ref_energyloss = (24.318829702548342**2.) * 5 ref_forceloss = (144.70279593472887**2.) * 5 ref_dloss_dparameters = np.array([ 0, 0, 0, 0, 0, 0, 0.01374139170953901, 0.36318423812749656, 0.028312691567496464, 0.6012336354445753, 0.9659002689921986, -1.2897765357544038, -0.5718958286530584, -2.642565840915077, -1.1960394346870424, 0, 0, -2.7256370964673238, -0.9080177898160631, -0.7739945904033205, -0.29157882294526083, -2.0599825024556027, -0.6156371996742152, -0.006086514109432934, -0.8296782839032163, 0.0008092653341775424, 0.04161306816722683, 0.0034264692325982156, -0.9578001030483714, -0.006281927374160914, -0.28835874344086, -4.245775886469167, -4.317410633818672, -8.02385959091948, -3.240512651984099, -27.289853042932705, -26.81776520493048, -82.45104200076496, -80.68164887277251 ]) ref_energy_maxresid = 54.21913802238612 ref_force_maxresid = 791.6734866205463 # Testing pure-python and fortran versions of Gaussian-neural on different # number of processes for fortran in [False, True]: for cores in range(1, 6): label = 'train-nonperiodic/%s-%i' % (fortran, cores) print(label) calc = Amp(descriptor=Gaussian( cutoff=6.5, Gs=Gs, fortran=fortran, ), model=NeuralNetwork( hiddenlayers=hiddenlayers, weights=weights, scalings=scalings, activation='sigmoid', regressor=regressor, fortran=fortran, ), label=label, dblabel=label, cores=cores) lossfunction = LossFunction(convergence=convergence) calc.model.lossfunction = lossfunction calc.train(images=images, ) diff = abs(calc.model.lossfunction.loss - ref_loss) print("diff at 204 =", diff) assert (diff < 10.**(-10.)), \ 'Calculated value of loss function is wrong!' diff = abs(calc.model.lossfunction.energy_loss - ref_energyloss) assert (diff < 10.**(-10.)), \ 'Calculated value of energy per atom RMSE is wrong!' diff = abs(calc.model.lossfunction.force_loss - ref_forceloss) assert (diff < 10 ** (-10.)), \ 'Calculated value of force RMSE is wrong!' diff = abs(calc.model.lossfunction.energy_maxresid - ref_energy_maxresid) assert (diff < 10.**(-10.)), \ 'Calculated value of energy per atom max residual is wrong!' diff = abs(calc.model.lossfunction.force_maxresid - ref_force_maxresid) assert (diff < 10 ** (-10.)), \ 'Calculated value of force max residual is wrong!' for _ in range(len(ref_dloss_dparameters)): diff = abs(calc.model.lossfunction.dloss_dparameters[_] - ref_dloss_dparameters[_]) assert(diff < 10 ** (-12.)), \ "Calculated value of loss function derivative is wrong!" dblabel = label secondlabel = '_' + label calc = Amp(descriptor=Gaussian( cutoff=6.5, Gs=Gs, fortran=fortran, ), model=NeuralNetwork( hiddenlayers=hiddenlayers, weights=weights, scalings=scalings, activation='sigmoid', regressor=regressor, fortran=fortran, ), label=secondlabel, dblabel=dblabel, cores=cores) lossfunction = LossFunction(convergence=convergence) calc.model.lossfunction = lossfunction calc.train(images=images, ) diff = abs(calc.model.lossfunction.loss - ref_loss) assert (diff < 10.**(-10.)), \ 'Calculated value of loss function is wrong!' diff = abs(calc.model.lossfunction.energy_loss - ref_energyloss) assert (diff < 10.**(-10.)), \ 'Calculated value of energy per atom RMSE is wrong!' diff = abs(calc.model.lossfunction.force_loss - ref_forceloss) assert (diff < 10 ** (-10.)), \ 'Calculated value of force RMSE is wrong!' diff = abs(calc.model.lossfunction.energy_maxresid - ref_energy_maxresid) assert (diff < 10.**(-10.)), \ 'Calculated value of energy per atom max residual is wrong!' diff = abs(calc.model.lossfunction.force_maxresid - ref_force_maxresid) assert (diff < 10 ** (-10.)), \ 'Calculated value of force max residual is wrong!' for _ in range(len(ref_dloss_dparameters)): diff = abs(calc.model.lossfunction.dloss_dparameters[_] - ref_dloss_dparameters[_]) assert(diff < 10 ** (-12.)), \ 'Calculated value of loss function derivative 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)
G = {} hiddenlayers = {} for el in elements: G[el] = Gf hiddenlayers[el] = layer_config if use_tensorflow: from amp.model.tflow import NeuralNetwork my_model = NeuralNetwork(hiddenlayers=hiddenlayers, force_coefficient=None) else: from amp.model.neuralnetwork import NeuralNetwork my_model = NeuralNetwork(hiddenlayers=hiddenlayers) MLIP = Amp(descriptor=Gaussian(Gs=G, cutoff=cutoff), model=my_model) MLIP.model.checkpoints = checkpoint_interval MLIP.cores['localhost'] = cores from amp.utilities import Logger, make_filename MLIP._log = Logger(make_filename('', log_file)) ############### parsing images ########## from ase import io from glob import glob import time struct_types = ['known', 'polymorphD3', 'random'] dyn_types = ['md', 'relax', 'sp'] image_list = []