Inference using CGCNN Model¶

In this notebook we show how to perform inference using GT4SD and CGCNN-based models. The current existing models (algorithm_version=v0) and the sample dataset have been obtained from the official CGCNN repository.

Formation Energy¶

This method predicts the formation energy per atom using the CGCNN framework (unit eV/atom).

In [ ]:

from gt4sd.properties.crystals.core import FormationEnergyParameters, FormationEnergy

model_parameters = FormationEnergyParameters(algorithm_version="v0")
model = FormationEnergy(model_parameters)

model(input="cgcnn-sample")

Absolute Energy¶

This method predicts the absolute energy of crystals using the CGCNN framework (unit eV/atom).

In [ ]:

from gt4sd.properties.crystals.core import AbsoluteEnergy, AbsoluteEnergyParameters

model_parameters = AbsoluteEnergyParameters(algorithm_version="v0")
model = AbsoluteEnergy(model_parameters)

model(input="cgcnn-sample")

Band Gap¶

This method predicts the band gap of crystals using the CGCNN framework (unit eV).

In [ ]:

from gt4sd.properties.crystals.core import BandGapParameters, BandGap

model_parameters = BandGapParameters(algorithm_version="v0")
model = BandGap(model_parameters)

model(input="cgcnn-sample")

Fermi Energy¶

This method predicts the Fermi energy of crystals using the CGCNN framework (unit eV/atom).

In [ ]:

from gt4sd.properties.crystals.core import FermiEnergyParameters, FermiEnergy

model_parameters = FermiEnergyParameters(algorithm_version="v0")
model = FermiEnergy(model_parameters)

model(input="cgcnn-sample")

Bulk Moduli¶

This method predicts the bulk moduli of crystals using the CGCNN framework (unit log(GPa)).

In [ ]:

from gt4sd.properties.crystals.core import BulkModuliParameters, BulkModuli

model_parameters = BulkModuliParameters(algorithm_version="v0")
model = BulkModuli(model_parameters)

model(input="cgcnn-sample")

Shear Moduli¶

This method predicts the shear moduli of crystals using the CGCNN framework (unit log(GPa)).

In [ ]:

from gt4sd.properties.crystals.core import ShearModuliParameters, ShearModuli

model_parameters = ShearModuliParameters(algorithm_version="v0")
model = ShearModuli(model_parameters)

model(input="cgcnn-sample")

Poisson Ratio¶

This method predicts the poisson ratio of crystals using the CGCNN framework.

In [ ]:

from gt4sd.properties.crystals.core import PoissonRatioParameters, PoissonRatio

model_parameters = PoissonRatioParameters(algorithm_version="v0")
model = PoissonRatio(model_parameters)

model(input="cgcnn-sample")

Metal-Semiconductor classifier¶

This method predicts if the provided crystals are metal (1) or semiconductors (0) using the CGCNN framework.

In [ ]:

from gt4sd.properties.crystals.core import MetalSemiconductorClassifierParameters, MetalSemiconductorClassifier

model_parameters = MetalSemiconductorClassifierParameters(algorithm_version="v0")
model = MetalSemiconductorClassifier(model_parameters)

model(input="cgcnn-sample")