torchcell.sga.NormalizationConfig

class NormalizationConfig(*, min_size: float = 1.0, exclude_low_circularity: bool = True, wt_name: str = 'BY4741', blank_name: str = 'Blank_media', row_col_correction: bool = True, spatial_correction: bool = True, spatial_radius: Annotated[int, Ge(ge=1)] = 2, spatial_min_neighbors: Annotated[int, Ge(ge=1)] = 4, jackknife: bool = True, jackknife_z: Annotated[float, Gt(gt=0)] = 3.5, cap_norm: float | None = None)

Bases: BaseModel

Knobs for the normalization stage. Defaults follow the SGA spirit but are adapted to a randomized single-KO layout (see class docstring in models).

model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].