​
Functions

​
check_tuner

edgeimpulse.tuner.check_tuner(
	timeout_sec: int | None = None,
	wait_for_completion: bool = True
) ‑> edgeimpulse_api.models.optimize_state_response.OptimizeStateResponse
Check the current state of the tuner and optionally waits until the tuner has completed.
Parameters
timeout_secint | None = None
wait_for_completionbool = True
Returns
edgeimpulse_api.models.optimize_state_response.OptimizeStateResponse

​
get_tuner_run_state

edgeimpulse.tuner.get_tuner_run_state(
	tuner_coordinator_job_id: int
) ‑> edgeimpulse_api.models.optimize_state_response.OptimizeStateResponse
Retrieve the current state of the tuner run. Returns: OptimizeStateResponse: The OptimizeStateResponse object representing the current Tuner state.
Parameters
tuner_coordinator_job_idint
Returns
edgeimpulse_api.models.optimize_state_response.OptimizeStateResponse

​
list_tuner_runs

edgeimpulse.tuner.list_tuner_runs(
	
) ‑> edgeimpulse_api.models.list_tuner_runs_response.ListTunerRunsResponse
List the tuner runs that have been done in the current project. Returns: ListTunerRunsResponse: An object containing all the tuner runs
Returns
edgeimpulse_api.models.list_tuner_runs_response.ListTunerRunsResponse
edgeimpulse.tuner.print_tuner_coordinator_logs(
	limit: int = 500
) ‑> None
Retrieve and print logs for the tuner coordinator job. Returns: None
Parameters
limitint = 500
Returns
None
edgeimpulse.tuner.print_tuner_job_logs(
	limit: int = 500
) ‑> None
Retrieve and print logs for the tuner job. Returns: None
Parameters
limitint = 500
Returns
None

​
set_impulse_from_trial

edgeimpulse.tuner.set_impulse_from_trial(
	trial_id: str,
	timeout_sec: float | None = None,
	wait_for_completion: bool | None = True
) ‑> edgeimpulse_api.models.start_job_response.StartJobResponse
Replace the current Impulse configuration with one found in a trial fromm the tuner.
Parameters
trial_idstr
timeout_secfloat | None = None
wait_for_completionbool | None = True
Returns
edgeimpulse_api.models.start_job_response.StartJobResponse

​
start_custom_tuner

edgeimpulse.tuner.start_custom_tuner(
	config: edgeimpulse_api.models.optimize_config.OptimizeConfig
) ‑> edgeimpulse_api.models.start_job_response.StartJobResponse
Start a tuner job with custom configuration.
Parameters
configedgeimpulse_api.models.optimize_config.OptimizeConfig
Returns
edgeimpulse_api.models.start_job_response.StartJobResponse

​
start_tuner

edgeimpulse.tuner.start_tuner(
	space: List[edgeimpulse_api.models.tuner_space_impulse.TunerSpaceImpulse],
	target_device: str,
	target_latency: int,
	tuning_max_trials: int | None = None,
	name: str | None = None
) ‑> edgeimpulse_api.models.start_job_response.StartJobResponse
Start the EON tuner with default settings. Use start_custom_tuner to specify config.
Parameters
spaceList[edgeimpulse_api.models.tuner_space_impulse.TunerSpaceImpulse]
target_devicestr
target_latencyint
tuning_max_trialsint | None = None
namestr | None = None
Returns
edgeimpulse_api.models.start_job_response.StartJobResponse

​
tuner_report_as_df

edgeimpulse.tuner.tuner_report_as_df(
	state: edgeimpulse_api.models.optimize_state_response.OptimizeStateResponse
)
Get a tuner trial report dataframe with model metrics and block configuration. This method needs pandas to be installed. Generate a dataframe on the tuner trials including used input, model, learn block configuration and model validation metrics.
Parameters
stateedgeimpulse_api.models.optimize_state_response.OptimizeStateResponse