프로세서 버전 학습

프로세서의 새 학습 작업 시작

더 살펴보기

이 코드 샘플이 포함된 자세한 문서는 다음을 참조하세요.

코드 샘플

Python

자세한 내용은 Document AI Python API 참고 문서를 참고하세요.

Document AI에 인증하려면 애플리케이션 기본 사용자 인증 정보를 설정합니다. 자세한 내용은 로컬 개발 환경의 인증 설정을 참조하세요.


from typing import Optional

from google.api_core.client_options import ClientOptions
from google.cloud import documentai  # type: ignore

# TODO(developer): Uncomment these variables before running the sample.
# project_id = 'YOUR_PROJECT_ID'
# location = 'YOUR_PROCESSOR_LOCATION' # Format is 'us' or 'eu'
# processor_id = 'YOUR_PROCESSOR_ID'
# processor_version_display_name = 'new-processor-version'
# train_data_uri = 'gs://bucket/directory/' # (Optional)
# test_data_uri = 'gs://bucket/directory/' # (Optional)


def train_processor_version_sample(
    project_id: str,
    location: str,
    processor_id: str,
    processor_version_display_name: str,
    train_data_uri: Optional[str] = None,
    test_data_uri: Optional[str] = None,
) -> None:
    # You must set the api_endpoint if you use a location other than 'us', e.g.:
    opts = ClientOptions(api_endpoint=f"{location}-documentai.googleapis.com")

    client = documentai.DocumentProcessorServiceClient(client_options=opts)

    # The full resource name of the processor
    # e.g. `projects/{project_id}/locations/{location}/processors/{processor_id}
    parent = client.processor_path(project_id, location, processor_id)

    processor_version = documentai.ProcessorVersion(
        display_name=processor_version_display_name
    )

    # If train/test data is not supplied, the default sets in the Cloud Console will be used
    input_data = documentai.TrainProcessorVersionRequest.InputData(
        training_documents=documentai.BatchDocumentsInputConfig(
            gcs_prefix=documentai.GcsPrefix(gcs_uri_prefix=train_data_uri)
        ),
        test_documents=documentai.BatchDocumentsInputConfig(
            gcs_prefix=documentai.GcsPrefix(gcs_uri_prefix=test_data_uri)
        ),
    )

    request = documentai.TrainProcessorVersionRequest(
        parent=parent, processor_version=processor_version, input_data=input_data
    )

    operation = client.train_processor_version(request=request)
    # Print operation details
    print(operation.operation.name)
    # Wait for operation to complete
    response = documentai.TrainProcessorVersionResponse(operation.result())

    metadata = documentai.TrainProcessorVersionMetadata(operation.metadata)

    print(f"New Processor Version:{response.processor_version}")
    print(f"Training Set Validation: {metadata.training_dataset_validation}")
    print(f"Test Set Validation: {metadata.test_dataset_validation}")

다음 단계

다른 Google Cloud 제품의 코드 샘플을 검색하고 필터링하려면 Google Cloud 샘플 브라우저 참조하기