MinMaxNormalize#

class MinMaxNormalize[source]#

Bases: ImageOnlyTransform

Albumentations transform that normalizes image to desired min and max values.

This will shift and scale the image appropriately to achieve the desired min and max.

Attributes

`call_backup`
`target_dependence`
`targets`
`targets_as_params`

__init__(min_val=0.0, max_val=1.0, dtype=5, always_apply=False, p=1.0)[source]#

Constructor.

Parameters

min_val – the minimum value that output should have
max_val – the maximum value that output should have
dtype – the dtype of output image

Methods

`__init__`([min_val, max_val, dtype, ...])	Constructor.
`add_targets`(additional_targets)	Add targets to transform them the same way as one of existing targets ex: {'target_image': 'image'} ex: {'obj1_mask': 'mask', 'obj2_mask': 'mask'} by the way you must have at least one object with key 'image'
`apply`(image, **params)
`apply_with_params`(params, args, *kwargs)
`get_base_init_args`()
`get_class_fullname`()
`get_dict_with_id`()
`get_params`()
`get_params_dependent_on_targets`(params)
`get_transform_init_args`()
`get_transform_init_args_names`()
`is_serializable`()
`set_deterministic`(flag[, save_key])
`to_dict`([on_not_implemented_error])	Take a transform pipeline and convert it to a serializable representation that uses only standard python data types: dictionaries, lists, strings, integers, and floats.
`to_dict_private`()
`update_params`(params, **kwargs)

__init__(min_val=0.0, max_val=1.0, dtype=5, always_apply=False, p=1.0)[source]#

Constructor.

Parameters

min_val – the minimum value that output should have
max_val – the maximum value that output should have
dtype – the dtype of output image

add_targets(additional_targets: Dict[str, str]) → None#

Add targets to transform them the same way as one of existing targets ex: {‘target_image’: ‘image’} ex: {‘obj1_mask’: ‘mask’, ‘obj2_mask’: ‘mask’} by the way you must have at least one object with key ‘image’

Parameters: additional_targets (dict) – keys - new target name, values - old target name. ex: {‘image2’: ‘image’}
Return type: None

apply(image, **params)[source]#

apply_with_params(params: Dict[str, Any], *args: Any, **kwargs: Any) → Dict[str, Any]#

Parameters

params (Dict[str, Any]) –
args (Any) –
kwargs (Any) –

Return type

Dict[str, Any]

get_base_init_args() → Dict[str, Any]#

Return type: Dict[str, Any]

classmethod get_class_fullname() → str#

Return type: str

get_dict_with_id() → Dict[str, Any]#

Return type: Dict[str, Any]

get_params() → Dict[str, Any]#

Return type: Dict[str, Any]

get_params_dependent_on_targets(params: Dict[str, Any]) → Dict[str, Any]#

Parameters: params (Dict[str, Any]) –
Return type: Dict[str, Any]

get_transform_init_args() → Dict[str, Any]#

Return type: Dict[str, Any]

get_transform_init_args_names()[source]#

classmethod is_serializable() → bool#

Return type: bool

set_deterministic(flag: bool, save_key: str = 'replay') → BasicTransform#

Parameters

flag (bool) –
save_key (str) –

Return type

BasicTransform

to_dict(on_not_implemented_error: str = 'raise') → Dict[str, Any]#

Take a transform pipeline and convert it to a serializable representation that uses only standard python data types: dictionaries, lists, strings, integers, and floats.

Parameters

self – A transform that should be serialized. If the transform doesn’t implement the to_dict method and on_not_implemented_error equals to ‘raise’ then NotImplementedError is raised. If on_not_implemented_error equals to ‘warn’ then NotImplementedError will be ignored but no transform parameters will be serialized.
on_not_implemented_error (str) – raise or warn.

Return type

Dict[str, Any]

to_dict_private() → Dict[str, Any]#

Return type: Dict[str, Any]

update_params(params: Dict[str, Any], **kwargs: Any) → Dict[str, Any]#

Parameters

params (Dict[str, Any]) –
kwargs (Any) –

Return type

Dict[str, Any]

call_backup = None#

fill_value: ColorType#

interpolation: Union[int, Interpolation]#

mask_fill_value: Optional[ColorType]#

property target_dependence: Dict[str, Any]#

property targets: Dict[str, Callable[[...], Any]]#

property targets_as_params: List[str]#