mediapipe_model_maker.model_util.convert_to_tflite

Converts the input Keras model to TFLite format.

Main aliases

mediapipe_model_maker.face_stylizer.face_stylizer.face_stylizer_options.model_opt.loss_functions.model_util.convert_to_tflite, mediapipe_model_maker.face_stylizer.face_stylizer.loss_functions.model_util.convert_to_tflite, mediapipe_model_maker.face_stylizer.face_stylizer.model_opt.loss_functions.model_util.convert_to_tflite, mediapipe_model_maker.face_stylizer.face_stylizer.model_util.convert_to_tflite, mediapipe_model_maker.face_stylizer.face_stylizer_options.model_opt.loss_functions.model_util.convert_to_tflite, mediapipe_model_maker.face_stylizer.model_options.loss_functions.model_util.convert_to_tflite

 
mediapipe_model_maker.model_util.convert_to_tflite(
    model: tf.keras.Model,
    quantization_config: Optional[mediapipe_model_maker.quantization.QuantizationConfig] = None,
    supported_ops: Tuple[tf.lite.OpsSet, ...] = (tf.lite.OpsSet.TFLITE_BUILTINS,),
    preprocess: Optional[Callable[..., Any]] = None,
    allow_custom_ops: bool = False
) -> bytearray

model Keras model to be converted to TFLite.
quantization_config Configuration for post-training quantization.
supported_ops A list of supported ops in the converted TFLite file.
preprocess A callable to preprocess the representative dataset for quantization. The callable takes three arguments in order: feature, label, and is_training.
allow_custom_ops A boolean flag to enable custom ops in model conversion. Default to False.

bytearray of TFLite model