noether.core.schemas.normalizers¶

Attributes¶

`MeanStdNormalizerConfig`
`PositionNormalizerConfig`
`ShiftAndScaleNormalizerConfig`

noether.core.schemas.normalizers.validate_tensor(v)¶

class noether.core.schemas.normalizers.MeanStdNormalizerConfig(/, **data)¶

Bases: pydantic.BaseModel

mean: TorchTensor¶: mean to subtract from the input data. Can be a single value or a Sequence if we want to apply a different mean per dimension.

std: TorchTensor¶: standard deviation to divide the input data by. Can be a single value or a Sequence if we want to apply a different std per dimension.

logscale: bool = False¶: If true, the input data is assumed to be in log scale.

class noether.core.schemas.normalizers.PositionNormalizerConfig(/, **data)¶

Bases: pydantic.BaseModel

raw_pos_min: TorchTensor¶: Minimum raw position values of the entire simulation mesh. Can be a single value or a sequence of values.

raw_pos_max: TorchTensor¶: Maximum raw position values of the entire simulation mesh. Can be a single value or a sequence of values.

scale: float = None¶: Scaling factor, the coordinates will be scaled linearly between [0, scale]. Defaults to 1000.

check_min_max()¶

class noether.core.schemas.normalizers.ShiftAndScaleNormalizerConfig(/, **data)¶

Bases: pydantic.BaseModel

shift: TorchTensor¶: Value to subtract from the input data. Can be a single value or a Sequence if we want to apply a different shift per dimension. Assumed in log scale if logscale is True.

scale: TorchTensor¶: Value to divide the input data by. Can be a single value or a Sequence if we want to apply a different scale per dimension. Assumed in log scale if logscale is True.

logscale: bool = False¶: If true, the input data is assumed to be in log scale.

check_shift_scale()¶