mediapipe_model_maker.gesture_recognizer.gesture_recognizer.classifier.custom_model.CustomModel

The abstract base class that represents a custom TensorFlow model.

View aliases

Main aliases

mediapipe_model_maker.image_classifier.image_classifier.classifier.custom_model.CustomModel, mediapipe_model_maker.python.core.tasks.classifier.custom_model.CustomModel, mediapipe_model_maker.python.core.tasks.custom_model.CustomModel, mediapipe_model_maker.python.text.text_classifier.text_classifier.classifier.custom_model.CustomModel, mediapipe_model_maker.python.vision.gesture_recognizer.gesture_recognizer.classifier.custom_model.CustomModel, mediapipe_model_maker.python.vision.image_classifier.image_classifier.classifier.custom_model.CustomModel, mediapipe_model_maker.text_classifier.text_classifier.classifier.custom_model.CustomModel

mediapipe_model_maker.gesture_recognizer.gesture_recognizer.classifier.custom_model.CustomModel(
    model_spec: Any, shuffle: bool
)

Args
model_spec	Specification for the model.
shuffle	Whether the training data need be shuffled.

Methods

evaluate

View source

@abc.abstractmethod
evaluate(
    data: mediapipe_model_maker.quantization.ds.Dataset,
    **kwargs
)

Evaluates the model with the provided data.

export_tflite

View source

export_tflite(
    export_dir: str,
    tflite_filename: str = 'model.tflite',
    quantization_config: Optional[mediapipe_model_maker.quantization.QuantizationConfig] = None,
    preprocess: Optional[Callable[..., bool]] = None
)

Converts the model to requested formats.

Args
export_dir	The directory to save exported files.
tflite_filename	File name to save TFLite model. The full export path is {export_dir}/{tflite_filename}.
quantization_config	The configuration for model quantization.
preprocess	A callable to preprocess the representative dataset for quantization. The callable takes three arguments in order: feature, label, and is_training.

summary

View source

summary()

Prints a summary of the model.