예측은 학습된 머신러닝 모델 출력입니다. 이 페이지에서는 Vertex AI의 모델에서 예측을 수행할 수 있는 워크플로를 간략하게 설명합니다.
Vertex AI에서는 두 가지 예측 수행 방법을 제공합니다.
온라인 예측은 Endpoint에 배포된 모델로 전송된 동기식 요청입니다.
따라서 요청을 전송하기 전에 Model 리소스를 엔드포인트에 배포해야 합니다. 이렇게 하면 컴퓨팅 리소스가 모델과 연결되므로 모델이 짧은 지연 시간으로 온라인 예측을 제공할 수 있습니다. 애플리케이션 입력에 대한 응답으로 요청하거나 적시의 추론이 필요한 상황에서 요청하는 경우에 온라인 예측을 사용하세요.
일괄 예측은 엔드포인트에 배포되지 않은 모델에 전송된 비동기식 요청입니다. BatchPredictionJob 리소스로 요청을 Model 리소스에 직접 보냅니다. 즉각적인 응답이 필요하지 않고 단일 요청을 사용하여 누적된 데이터를 처리하고 싶은 경우에 일괄 예측을 사용하세요.
[[["이해하기 쉬움","easyToUnderstand","thumb-up"],["문제가 해결됨","solvedMyProblem","thumb-up"],["기타","otherUp","thumb-up"]],[["이해하기 어려움","hardToUnderstand","thumb-down"],["잘못된 정보 또는 샘플 코드","incorrectInformationOrSampleCode","thumb-down"],["필요한 정보/샘플이 없음","missingTheInformationSamplesINeed","thumb-down"],["번역 문제","translationIssue","thumb-down"],["기타","otherDown","thumb-down"]],["최종 업데이트: 2025-09-04(UTC)"],[],[],null,["# Overview of getting inferences on Vertex AI\n\nAn inference is the output of a trained machine learning model. This page\nprovides an overview of the workflow for getting inferences from your models on\nVertex AI.\n\nVertex AI offers two methods for getting inferences:\n\n- **Online inferences** are synchronous requests made to a model that is deployed to an [`Endpoint`](/vertex-ai/docs/reference/rest/v1/projects.locations.endpoints). Therefore, before sending a request, you must first deploy the [`Model`](/vertex-ai/docs/reference/rest/v1/projects.locations.models) resource to an endpoint. This associates [compute resources](/vertex-ai/docs/predictions/configure-compute) with the model so that the model can serve online inferences with low latency. Use online inferences when you are making requests in response to application input or in situations that require timely inference.\n- are asynchronous requests made to a model that isn't deployed to an endpoint. You send the request (as a [`BatchPredictionJob`](/vertex-ai/docs/reference/rest/v1/projects.locations.batchPredictionJobs) resource) directly to the `Model` resource. Use batch inferences when you don't require an immediate response and want to process accumulated data by using a single request.\n\nGet inferences from custom trained models\n-----------------------------------------\n\nTo get inferences, you must first [import your\nmodel](/vertex-ai/docs/model-registry/import-model). After it's imported, it becomes a\n[`Model`](/vertex-ai/docs/reference/rest/v1/projects.locations.models) resource that is visible in\n[Vertex AI Model Registry](/vertex-ai/docs/model-registry/introduction).\n\nThen, read the following documentation to learn how to get inferences:\n\n- [Get batch inferences](/vertex-ai/docs/predictions/get-batch-predictions)\n\n Or\n- [Deploy model to endpoint](/vertex-ai/docs/general/deployment) and\n [get online inferences](/vertex-ai/docs/predictions/get-online-predictions).\n\nGet inferences from AutoML models\n---------------------------------\n\nUnlike custom trained models, AutoML models are automatically imported into the\nVertex AI Model Registry after training.\n\nOther than that, the workflow for AutoML models is similar, but varies slightly\nbased on your data type and model objective. The documentation for getting\nAutoML inferences is located alongside the other AutoML documentation. Here are links\nto the documentation:\n\n### Image\n\nLearn how to get inferences from the following types of image AutoML models:\n\n- [Image classification models](/vertex-ai/docs/image-data/classification/get-predictions)\n- [Image object detection models](/vertex-ai/docs/image-data/object-detection/get-predictions)\n\n### Tabular\n\nLearn how to get inferences from the following types of tabular AutoML models:\n\n- Tabular classification and regression models\n\n - [Online inferences](/vertex-ai/docs/tabular-data/classification-regression/get-online-predictions)\n - [Batch inferences](/vertex-ai/docs/tabular-data/classification-regression/get-batch-predictions)\n- [Tabular forecasting models](/vertex-ai/docs/tabular-data/forecasting/get-predictions) (batch inferences only)\n\n### Video\n\nLearn how to get inferences from the following types of video AutoML models:\n\n- [Video action recognition models](/vertex-ai/docs/video-data/action-recognition/get-predictions) (batch inferences only)\n- [Video classification models](/vertex-ai/docs/video-data/classification/get-predictions) (batch inferences only)\n- [Video object tracking models](/vertex-ai/docs/video-data/object-tracking/get-predictions) (batch inferences only)\n\nGet inferences from BigQuery ML models\n--------------------------------------\n\nYou can get inferences from BigQuery ML models in two ways:\n\n- Request batch inferences directly from the model in BigQuery ML.\n- Register the models directly with the Model Registry, without exporting them from BigQuery ML or importing them into the Model Registry."]]