imlab.classifier.Classifier

class imlab.classifier.Classifier(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)

Bases: Wrapper

Classifier.

__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)

__init__.

Parameters

• weight (str) –

• model_type (str) –

• image_size (int) –

• model (object) –

• preprocess (callable) –

• decode (callable) –

• num_class (int) –

Methods

__init__([weight, model_type, image_size, ...])	__init__.
dump(file_handler)	dump.
norm_input(image)	norm_input.
predict(image[, num])	predict.

dump(file_handler) → None

dump.

Parameters

file_handler –

Return type

None

norm_input(image: object) → ndarray

norm_input. normalize input

Parameters

image (object) –

Return type

np.ndarray

predict(image: object, num: int = 1) -> (<class 'str'>, <class 'float'>)

predict. predict image classe

Parameters

• image (object) –

• num (int) – number of result, if num==0, return a generator

Return type

(str, float)