Inference Model

netspresso.np_qai.benchmarker.NPQAIBenchmarker.inference_model(input_model_path, target_device_name, inputs, job_name=None, options=InferenceOptions(), retry=True)

Inference a model on a device in the QAI hub.

Parameters:

Name	Type	Description	Default
input_model_path	Union[str, Path]	The path to the input model.	required
target_device_name	Union[Device, List[Device]]	The device to benchmark the model on.	required
inputs	Union[Dataset, DatasetEntries, str]	The input data to use for the inference.	required
job_name	Optional[str]	The name of the job.	None
options	Union[InferenceOptions, str]	The options to use for the inference.	InferenceOptions()
retry	bool	Whether to retry the inference if it fails.	True

Returns:

Type	Description
Union[InferenceJob, List[InferenceJob]]	Union[InferenceJob, List[InferenceJob]]: Returns an inference job object if successful.

Note

For details, see submit_inference_job in QAI Hub API.