InferenceJob

class InferenceJob(job_pb, owner, device, model, date, inputs, project_id)

Inference job for a model, user provided inputs, and a device.

An inference job should not be constructed directly. It is constructed by the hub client through submit_inference_job(), or get_job().

device

The device for this job.

Type:

Device

model

The model for the job.

Type:

Model

date

The time this job was submitted.

Type:

datetime

inputs

The inputs provided by user.

Type:

Dataset

disable_sharing()

Disable all sharing for this job.

반환 형식:

None

download_artifacts_for_type(output_dir, artifact_type)

Downloads all artifacts of a given type for this job.

If the job is not yet complete, this function will block until completion. If the requested artifact type is not available, returns an empty list. Existing files in the output directory will be overwritten.

매개변수:
  • output_dir (str) – Directory to save artifacts to. Created if it does not exist.

  • artifact_type (JobArtifactType) – The type of artifact to download.

반환:

Paths to the downloaded artifact files.

반환 형식:

list[str]

download_job_logs(output_dir)

Downloads all available log artifacts for this job.

If the job is not yet complete, this function will block until completion.

매개변수:

output_dir (str) – Directory to save log files to. Created if it does not exist.

반환:

Paths to the downloaded log files.

반환 형식:

list[str]

download_output_data(filename=None)

Returns the downloaded output data, either in memory or as a h5f file.

If the job is not ready, this function will block until completion.

매개변수:

filename (Optional[str]) – If filename is specified the output data is downloaded to file, otherwise to memory.

반환:

The downloaded output data, filename, or None if the job failed.

반환 형식:

DatasetEntries | str | None

download_results(artifacts_dir)

Returns all the results of an inference job.

If the job is not ready, this function will block until completion.

매개변수:

artifacts_dir (str) – Directory name where the job artifacts are stored. If the directory does not exist, it is created.

반환:

Job results.

반환 형식:

InferenceJobResult

get_available_artifacts()

Returns the list of artifact types available for download on this job.

If the job is not yet complete, this function will block until completion.

참고

The availability of specific artifact types may change without notice.

반환:

Available artifact types.

반환 형식:

list[JobArtifactType]

get_output_dataset()

Returns the output dataset for a job.

If the job is not ready, this function will block until completion.

반환:

The output data if the job succeeded

반환 형식:

Dataset | None

get_sharing()

Get the list of email addresses of users that this job has been shared with.

반환 형식:

list[str]

get_status()

Returns the status of a job.

반환:

The status of the job

반환 형식:

JobStatus

modify_sharing(add_emails=[], delete_emails=[])

Modifies the list of users that the job is shared with.

All assets (models, datasets, artifacts, etc.) associated with the job will also be shared. For inference and profile jobs, the corresponding compile and link jobs (if any) will also be shared.

반환 형식:

None

set_name(job_name)

Sets the name of a job to the specified value.

반환 형식:

None

property url: str

Returns the URL for the job.

반환:

The URL for the job.

반환 형식:

str

wait(timeout=None)

Block until this job finishes.

매개변수:

timeout (Optional[int]) –

If provided, a TimeoutError will be raised after waiting this many seconds.

If None, this client will not time out the job, meaning it will block an indefinite amount of time waiting for the job to finish.

HOWEVER, Qualcomm AI Hub will fail / time out any job a set amount of time after its creation. Therefore, even if timeout is None, the runtime of this method will still have a finite upper bound.

반환:

The final, “finished” (SUCCESS or FAILED) status for this job.

반환 형식:

str

예외 발생:

TimeoutError – Raised only if a client-side timeout occurs, when param “timeout” != None. If the Qualcomm AI Hub server times out the job, this error will NOT be raised, and a FAILED job status will be returned instead.