An error in specifying fingerprints manually

As discussed in the mailing list, there seems to be an error in fmodules when specifying a fingerprint manually. A self-contained script replicating the problem is below:
from amp import Amp
from amp.descriptor.gaussian import Gaussian
from amp.model.neuralnetwork import NeuralNetwork
from amp.model import LossFunction

import os
from ase import Atoms, Atom, units
import ase.io
from ase.calculators.emt import EMT
from ase.lattice.surface import fcc110
from ase.md.velocitydistribution import MaxwellBoltzmannDistribution
from ase.md import VelocityVerlet
from ase.constraints import FixAtoms

from amp import Amp
from amp.descriptor.gaussian import Gaussian
from amp.model.neuralnetwork import NeuralNetwork


def generate_data(count, filename='training.traj'):
    """Generates test or training data with a simple MD simulation."""
    if os.path.exists(filename):
        return
    traj = ase.io.Trajectory(filename, 'w')
    atoms = fcc110('Pt', (2, 2, 2), vacuum=7.)
    atoms.extend(Atoms([Atom('Cu', atoms[7].position + (0., 0., 2.5)),
                        Atom('Cu', atoms[7].position + (0., 0., 5.))]))
    atoms.set_constraint(FixAtoms(indices=[0, 2]))
    atoms.set_calculator(EMT())
    atoms.get_potential_energy()
    traj.write(atoms)
    MaxwellBoltzmannDistribution(atoms, 300. * units.kB)
    dyn = VelocityVerlet(atoms, dt=1. * units.fs)
    for step in range(count - 1):
        dyn.run(50)
        traj.write(atoms)


generate_data(2)

Gs={'Cu': [{'type': 'G2', 'element' : 'Cu', 'eta' : 0.000},
          {'type': 'G2', 'element' : 'Pt', 'eta' : 0.0000},
          {'type': 'G2', 'element' : 'Cu', 'eta' : 0.012},
          {'type': 'G2', 'element' : 'Pt', 'eta' : 0.0100},
          {'type': 'G2', 'element' : 'Cu', 'eta' : 0.030},
          {'type': 'G2', 'element' : 'Pt', 'eta' : 0.0240},
          {'type': 'G2', 'element' : 'Cu', 'eta' : 0.062},
          {'type': 'G4', 'elements' : ['Pt','Cu'], 'eta':0.000,'gamma': 1.0,'zeta': 6.0},
          {'type': 'G4', 'elements' : ['Pt','Pt'], 'eta':0.000,'gamma': 1.0,'zeta': 6.0},
          {'type': 'G4', 'elements' : ['Pt','Cu'], 'eta':0.000,'gamma':-1.0,'zeta': 6.0},
          {'type': 'G4', 'elements' : ['Pt','Pt'], 'eta':0.000,'gamma':-1.0,'zeta':2.15},
          {'type': 'G4', 'elements' : ['Pt','Cu'], 'eta':0.000,'gamma': 1.0,'zeta':15.0},
          {'type': 'G4', 'elements' : ['Pt','Pt'], 'eta':0.000,'gamma': 1.0,'zeta':15.0},
          {'type': 'G4', 'elements' : ['Pt','Cu'], 'eta':0.000,'gamma':-1.0,'zeta':15.0},
          {'type': 'G4', 'elements' : ['Pt','Pt'], 'eta':0.000,'gamma':-1.0,'zeta': 2.9},
          {'type': 'G4', 'elements' : ['Pt','Cu'], 'eta':0.000,'gamma': 1.0,'zeta':68.0},
          {'type': 'G4', 'elements' : ['Pt','Pt'], 'eta':0.000,'gamma': 1.0,'zeta':68.0},
          {'type': 'G4', 'elements' : ['Pt','Cu'], 'eta':0.000,'gamma':-1.0,'zeta':68.0},
          {'type': 'G4', 'elements' : ['Pt','Pt'], 'eta':0.000,'gamma':-1.0,'zeta': 4.0}],
    'Pt': [{'type': 'G2', 'element' : 'Cu', 'eta' : 0.0000},
          {'type': 'G2', 'element' : 'Pt', 'eta' : 0.0000},
          {'type': 'G2', 'element' : 'Cu', 'eta' : 0.0100},
          {'type': 'G2', 'element' : 'Pt', 'eta' : 0.0085},
          {'type': 'G2', 'element' : 'Cu', 'eta' : 0.0240},
          {'type': 'G2', 'element' : 'Pt', 'eta' : 0.0220},
          {'type': 'G2', 'element' : 'Cu', 'eta' : 0.0480},
          {'type': 'G4', 'elements' : ['Cu','Cu'], 'eta':0.000,'gamma': 1.0,'zeta': 3.0},
          {'type': 'G4', 'elements' : ['Pt','Cu'], 'eta':0.000,'gamma': 1.0,'zeta': 3.0},
          {'type': 'G4', 'elements' : ['Pt','Pt'], 'eta':0.000,'gamma': 1.0,'zeta': 3.0},
          {'type': 'G4', 'elements' : ['Cu','Cu'], 'eta':0.000,'gamma':-1.0,'zeta':1.65},
          {'type': 'G4', 'elements' : ['Pt','Cu'], 'eta':0.000,'gamma':-1.0,'zeta': 3.0},
          {'type': 'G4', 'elements' : ['Pt','Pt'], 'eta':0.000,'gamma':-1.0,'zeta': 3.0},
          {'type': 'G4', 'elements' : ['Cu','Cu'], 'eta':0.000,'gamma': 1.0,'zeta': 6.0},
          {'type': 'G4', 'elements' : ['Pt','Cu'], 'eta':0.000,'gamma': 1.0,'zeta': 6.0},
          {'type': 'G4', 'elements' : ['Pt','Pt'], 'eta':0.000,'gamma': 1.0,'zeta': 6.0},
          {'type': 'G4', 'elements' : ['Cu','Cu'], 'eta':0.000,'gamma':-1.0,'zeta':2.15},
          {'type': 'G4', 'elements' : ['Pt','Cu'], 'eta':0.000,'gamma':-1.0,'zeta': 6.0},
          {'type': 'G4', 'elements' : ['Pt','Pt'], 'eta':0.000,'gamma':-1.0,'zeta': 6.0},
          {'type': 'G4', 'elements' : ['Cu','Cu'], 'eta':0.000,'gamma': 1.0,'zeta':15.0},
          {'type': 'G4', 'elements' : ['Pt','Cu'], 'eta':0.000,'gamma': 1.0,'zeta':15.0},
          {'type': 'G4', 'elements' : ['Pt','Pt'], 'eta':0.000,'gamma': 1.0,'zeta':15.0},
          {'type': 'G4', 'elements' : ['Cu','Cu'], 'eta':0.000,'gamma':-1.0,'zeta': 2.9},
          {'type': 'G4', 'elements' : ['Pt','Cu'], 'eta':0.000,'gamma':-1.0,'zeta':15.0},
          {'type': 'G4', 'elements' : ['Pt','Pt'], 'eta':0.000,'gamma':-1.0,'zeta':15.0},
          {'type': 'G4', 'elements' : ['Cu','Cu'], 'eta':0.000,'gamma': 1.0,'zeta':68.0},
          {'type': 'G4', 'elements' : ['Pt','Cu'], 'eta':0.000,'gamma': 1.0,'zeta':68.0},
          {'type': 'G4', 'elements' : ['Pt','Pt'], 'eta':0.000,'gamma': 1.0,'zeta':68.0},
          {'type': 'G4', 'elements' : ['Cu','Cu'], 'eta':0.000,'gamma':-1.0,'zeta': 4.0},
          {'type': 'G4', 'elements' : ['Pt','Cu'], 'eta':0.000,'gamma':-1.0,'zeta':68.0},
          {'type': 'G4', 'elements' : ['Pt','Pt'], 'eta':0.000,'gamma':-1.0,'zeta':68.0}]}
#cores = {'node241': 16, 'node242': 16}
hl={'Pt': (20,20), 'Cu': (20,20)}
calc = Amp(descriptor=Gaussian(cutoff=11.,Gs=Gs,fortran=True, mode='atom-centered'),
           model=NeuralNetwork(hiddenlayers=hl),
           label='calc',
       cores=1,
       )
calc.model.lossfunction = LossFunction(convergence={'energy_rmse': 0.02,
                                                    'force_rmse': 0.02})
calc.train(images='training.traj')
Comments (3)
