imlab.classifier_wrapper.Wrapper

class imlab.classifier_wrapper.Wrapper(weight: ~typing.Optional[str] = None, model_type: str = 'MobileNetV2', image_size: int = 300, model: ~typing.Optional[object] = None, preprocess: callable = <function preprocess>, decode: callable = <function decode>, num_class: int = 0, model_mod: str = 'use')

Bases: object

Wrapper. tensorflow wrapper

__init__(weight: ~typing.Optional[str] = None, model_type: str = 'MobileNetV2', image_size: int = 300, model: ~typing.Optional[object] = None, preprocess: callable = <function preprocess>, decode: callable = <function decode>, num_class: int = 0, model_mod: str = 'use') → None

__init__.

Parameters

• weight (str) – tensorflow weight

• model_type (str) – model type, can be MobileNetV2, resnet50,densenet121,inceptionv3

• image_size (int) –

• model (object) –

• preprocess (callable) –

• decode (callable) –

• num_class (int) –

• model_mod (str) –

Return type

None

Methods

__init__([weight, model_type, image_size, ...])	__init__.
norm_input(image)	norm_input.

norm_input(image: object) → ndarray

norm_input. normalize input

Parameters

image (object) –

Return type

np.ndarray