minmax

Minmax

Bases: NumpyOp

Normalize data using the minmax method.

Parameters:

Name	Type	Description	Default
inputs	Union[str, Iterable[str]]	Key(s) of images to be modified.	required
outputs	Union[str, Iterable[str]]	Key(s) into which to write the modified images.	required
mode	Union[None, str, Iterable[str]]	What mode(s) to execute this Op in. For example, "train", "eval", "test", or "infer". To execute regardless of mode, pass None. To execute in all modes except for a particular one, you can pass an argument like "!infer" or "!train".	None
ds_id	Union[None, str, Iterable[str]]	What dataset id(s) to execute this Op in. To execute regardless of ds_id, pass None. To execute in all ds_ids except for a particular one, you can pass an argument like "!ds1".	None
epsilon	float	A small value to prevent numeric instability in the division.	1e-07

Source code in fastestimator/fastestimator/op/numpyop/univariate/minmax.py

@traceable()
class Minmax(NumpyOp):
    """Normalize data using the minmax method.

    Args:
        inputs: Key(s) of images to be modified.
        outputs: Key(s) into which to write the modified images.
        mode: What mode(s) to execute this Op in. For example, "train", "eval", "test", or "infer". To execute
            regardless of mode, pass None. To execute in all modes except for a particular one, you can pass an argument
            like "!infer" or "!train".
        ds_id: What dataset id(s) to execute this Op in. To execute regardless of ds_id, pass None. To execute in all
            ds_ids except for a particular one, you can pass an argument like "!ds1".
        epsilon: A small value to prevent numeric instability in the division.
    """
    def __init__(self,
                 inputs: Union[str, Iterable[str]],
                 outputs: Union[str, Iterable[str]],
                 mode: Union[None, str, Iterable[str]] = None,
                 ds_id: Union[None, str, Iterable[str]] = None,
                 epsilon: float = 1e-7):
        super().__init__(inputs=inputs, outputs=outputs, mode=mode, ds_id=ds_id)
        self.epsilon = epsilon
        self.in_list, self.out_list = True, True

    def forward(self, data: List[np.ndarray], state: Dict[str, Any]) -> List[np.ndarray]:
        return [self._apply_minmax(elem) for elem in data]

    def _apply_minmax(self, data: np.ndarray) -> np.ndarray:
        data_max = np.max(data)
        data_min = np.min(data)
        data = (data - data_min) / max((data_max - data_min), self.epsilon)
        return data.astype(np.float32)