QuantizeJob

class QuantizeJob(job_pb, weights_dtype, activations_dtype, owner, model, date, shapes, calibration_dataset, project_id)

Quantize job for a model, a set of input specs, and a set of device.

A quantize job should not be constructed directly. It is constructed by the hub client through submit_quantize_job() or get_job().

model

The model for the job.

Type:

Model

date

The time this job was submitted.

Type:

datetime

shapes

The input specs for the model to be compiled.

Type:

InputSpecs

target_shapes

The input specs for the compiled model to run (profile or inference).

Type:

InputSpecs

calibration_dataset

The dataset used with post training quantization run during compilation.

Type:

Dataset | None

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_results(artifacts_dir)

Returns all the results of a job.

This includes compiled target model.

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:

QuantizeJobResult

download_target_model(filename=None)

Returns the downloaded target model, either in memory or as a file.

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

매개변수:

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

반환:

The downloaded target model, filename, or None if the job failed.

반환 형식:

TargetModel | str | None

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_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

get_target_model()

Returns the target model object. If the job is not ready, this function will block until completion.

반환:

The target model object, or None if the job failed.

반환 형식:

TargetModel | None

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.