afe.apis.loaded_net

Attributes

GroundTruth

Classes

LoadedNet

Functions

load_model(β†’Β LoadedNet)

Module Contents

afe.apis.loaded_net.GroundTruth
class afe.apis.loaded_net.LoadedNet(mod: afe._tvm._defines.TVMIRModule, layout: str, target: sima_utils.common.Platform, *, output_labels: list[str] | None, model_path: str | None)
execute(inputs: afe.apis.defines.InputValues, *, log_level: int = logging.NOTSET) → list[numpy.ndarray]
quantize(calibration_data: Iterable[afe.apis.defines.InputValues], quantization_config: afe.apis.defines.QuantizationParams, *, automatic_layout_conversion: bool = False, arm_only: bool = False, simulated_arm: bool = False, model_name: str | None = None, any_shape_on_mla: bool = False, log_level: int = logging.NOTSET) → afe.apis.model.Model
quantize_with_accuracy_feedback(calibration_data: Iterable[afe.apis.defines.InputValues], evaluation_data: Iterable[tuple[afe.apis.defines.InputValues, GroundTruth]], quantization_config: afe.apis.defines.QuantizationParams, *, accuracy_score: afe.driver.statistic.Statistic[tuple[list[numpy.ndarray], GroundTruth], float], target_accuracy: float, automatic_layout_conversion: bool = False, max_optimization_steps: int | None = None, model_name: str | None = None, any_shape_on_mla: bool = False, log_level: int = logging.NOTSET) → afe.apis.model.Model
convert_to_sima_quantization(*, requantization_mode: afe.ir.defines.RequantizationMode = RequantizationMode.sima, model_name: str | None = None, any_shape_on_mla: bool = False, log_level: int = logging.NOTSET) → afe.apis.model.Model
afe.apis.loaded_net.load_model(params: afe.load.importers.general_importer.ImporterParams, *, target: sima_utils.common.Platform = gen1_target, log_level: int = logging.NOTSET) → LoadedNet