Skip to content

JAX

model_navigator.api.jax

JAX optimize API.

optimize(model, model_params, dataloader, sample_count=DEFAULT_SAMPLE_COUNT, batching=True, target_formats=None, runners=None, profiler_config=None, workspace=None, verbose=False, debug=False, verify_func=None, custom_configs=None)

Function exports JAX model to all supported formats.

Parameters:

Name Type Description Default
model Callable

JAX forward function

required
model_params Any

JAX model parameters (weights)

required
dataloader SizedDataLoader

Sized iterable with data that will be feed to the model

required
sample_count int

Limits how many samples will be used from dataloader

DEFAULT_SAMPLE_COUNT
batching Optional[bool]

Enable or disable batching on first (index 0) dimension of the model

True
target_formats Optional[Union[Union[str, Format], Tuple[Union[str, Format], ...]]]

Target model formats for optimize process

None
runners Optional[Union[Union[str, Type[NavigatorRunner]], Tuple[Union[str, Type[NavigatorRunner]], ...]]]

Use only runners provided as paramter

None
profiler_config Optional[ProfilerConfig]

Profiling config

None
workspace Optional[Path]

Workspace where packages will be extracted

None
verbose bool

Enable verbose logging

False
debug bool

Enable debug logging from commands

False
verify_func Optional[VerifyFunction]

Function for additional model verifcation

None
custom_configs Optional[Sequence[CustomConfig]]

Sequence of CustomConfigs used to control produced artifacts

None

Returns:

Type Description
Package

Package descriptor representing created package.

Source code in model_navigator/api/jax.py
def optimize(
    model: Callable,
    model_params: Any,
    dataloader: SizedDataLoader,
    sample_count: int = DEFAULT_SAMPLE_COUNT,
    batching: Optional[bool] = True,
    target_formats: Optional[Union[Union[str, Format], Tuple[Union[str, Format], ...]]] = None,
    runners: Optional[Union[Union[str, Type[NavigatorRunner]], Tuple[Union[str, Type[NavigatorRunner]], ...]]] = None,
    profiler_config: Optional[ProfilerConfig] = None,
    workspace: Optional[Path] = None,
    verbose: bool = False,
    debug: bool = False,
    verify_func: Optional[VerifyFunction] = None,
    custom_configs: Optional[Sequence[CustomConfig]] = None,
) -> Package:
    """Function exports JAX model to all supported formats.

    Args:
        model: JAX forward function
        model_params: JAX model parameters (weights)
        dataloader: Sized iterable with data that will be feed to the model
        sample_count: Limits how many samples will be used from dataloader
        batching: Enable or disable batching on first (index 0) dimension of the model
        target_formats: Target model formats for optimize process
        runners: Use only runners provided as paramter
        profiler_config: Profiling config
        workspace: Workspace where packages will be extracted
        verbose: Enable verbose logging
        debug: Enable debug logging from commands
        verify_func: Function for additional model verifcation
        custom_configs: Sequence of CustomConfigs used to control produced artifacts

    Returns:
        Package descriptor representing created package.
    """
    if isinstance(model, str):
        model = Path(model)
    if workspace is None:
        workspace = get_default_workspace()
    if target_formats is None:
        target_formats = DEFAULT_JAX_TARGET_FORMATS

    sample = next(iter(dataloader))
    forward_kw_names = tuple(sample.keys()) if isinstance(sample, Mapping) else None

    if runners is None:
        runners = tuple(runner_registry.keys())

    if profiler_config is None:
        profiler_config = ProfilerConfig()

    target_formats_enums = enums.parse(target_formats, Format)
    runner_names = enums.parse(runners, lambda runner: runner if isinstance(runner, str) else runner.name())

    if Format.JAX not in target_formats_enums:
        target_formats_enums = (Format.JAX,) + target_formats_enums

    config = CommonConfig(
        Framework.JAX,
        model=JaxModel(model=model, params=model_params),
        dataloader=dataloader,
        forward_kw_names=forward_kw_names,
        workspace=workspace,
        target_formats=target_formats_enums,
        sample_count=sample_count,
        batch_dim=0 if batching else None,
        runner_names=runner_names,
        profiler_config=profiler_config,
        verbose=verbose,
        debug=debug,
        verify_func=verify_func,
        custom_configs=map_custom_configs(custom_configs=custom_configs),
    )

    models_config = ModelConfigBuilder.generate_model_config(
        framework=Framework.JAX,
        target_formats=target_formats_enums,
        custom_configs=custom_configs,
    )

    builders = [
        preprocessing_builder,
        jax_export_builder,
        tensorflow_conversion_builder,
        correctness_builder,
    ]
    if profiler_config.run_profiling:
        builders.append(profiling_builder)
    builders.append(verify_builder)

    package = PipelineManager.run(
        pipeline_builders=builders,
        config=config,
        models_config=models_config,
    )

    return package