> For the complete documentation index, see [llms.txt](https://docs.roboflow.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.roboflow.com/models/ko/readme.md).

# 모델

데이터셋에 최첨단 컴퓨터 비전 모델을 학습하세요. ML 전문 지식이나 GPU 설정이 필요 없습니다. Roboflow가 학습 인프라를 관리하고, 결과 모델을 배포할 수 있도록 호스팅합니다.

## 선택 및 학습

<table data-view="cards" data-search="false"><thead><tr><th></th><th></th><th data-hidden data-card-cover data-type="image">표지 이미지</th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>지원되는 모델</strong></td><td>Roboflow로 학습, 업로드, 배포할 수 있는 모든 모델과 각 모델이 실행되는 위치를 확인하세요.</td><td><a href="/files/e046d6620b91c1db204097a0a992e19d14c68d9f">/files/e046d6620b91c1db204097a0a992e19d14c68d9f</a></td><td><a href="/pages/5cf943ba42e0cfdbe4025171200843900cb50c36">/pages/5cf943ba42e0cfdbe4025171200843900cb50c36</a></td></tr><tr><td><strong>모델 학습</strong></td><td>대시보드, API, SDK 또는 CLI에서 학습 작업을 시작하세요.</td><td><a href="/files/c3652a8ce4d958a1e53bcda90bb7724feaf6a60e">/files/c3652a8ce4d958a1e53bcda90bb7724feaf6a60e</a></td><td><a href="/pages/baacb7d0f6c27d6a3fb7ce76d151b6cb0315ffb1">/pages/baacb7d0f6c27d6a3fb7ce76d151b6cb0315ffb1</a></td></tr><tr><td><strong>Roboflow 인스턴트</strong></td><td>첫 번째 승인된 주석으로부터 자동으로 학습된 모델입니다.</td><td><a href="/files/d09e7bf2f35c6b7366ad2409b10091d3f276a92d">/files/d09e7bf2f35c6b7366ad2409b10091d3f276a92d</a></td><td><a href="/pages/b49375c145bd7cc08786f4283daf1916c19d48c0">/pages/b49375c145bd7cc08786f4283daf1916c19d48c0</a></td></tr><tr><td><strong>Neural Architecture Search</strong></td><td>새로운 아키텍처를 발견하고 미세 조정하세요.</td><td><a href="/files/582b317a588a42eac11322fe19fa468a7b1e5f81">/files/582b317a588a42eac11322fe19fa468a7b1e5f81</a></td><td><a href="/pages/fc20ae2c8e86573cfe150b11eddd5f4363c9b233">/pages/fc20ae2c8e86573cfe150b11eddd5f4363c9b233</a></td></tr><tr><td><strong>Roboflow Rapid</strong></td><td>적은 양의 데이터 샘플로 몇 분 만에 작동하는 모델을 만드세요.</td><td><a href="/files/e701abd6ee93d66d1bbcfb3618a6f5da788965c0">/files/e701abd6ee93d66d1bbcfb3618a6f5da788965c0</a></td><td><a href="/pages/bb5673bbf271b3e91d647818282e89be93f74e3b">/pages/bb5673bbf271b3e91d647818282e89be93f74e3b</a></td></tr><tr><td><strong>체크포인트에서 학습</strong></td><td>기존 Roboflow Universe 모델에서 학습을 시작하세요.</td><td><a href="/files/ae2618c1f8fe1867f109e83041a2ee1afb7cf62a">/files/ae2618c1f8fe1867f109e83041a2ee1afb7cf62a</a></td><td><a href="/pages/0ad9715f3746f82bdd0fe11033da4b60ec2dbbfc">/pages/0ad9715f3746f82bdd0fe11033da4b60ec2dbbfc</a></td></tr></tbody></table>

타사 체크포인트에서도 학습할 수 있습니다. [Azure Vision](/models/ko/train/pro-third-party-training-integrations.md) 또는 [Google Cloud](/models/ko/train/train-from-google-cloud.md).

## 평가 및 이해

<table data-view="cards" data-search="false"><thead><tr><th></th><th></th><th data-hidden data-card-cover data-type="image">표지 이미지</th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>학습된 모델 평가</strong></td><td>평가 실행, mAP, 혼동 행렬.</td><td><a href="/files/e81a0d8095d13664d7b01d6624fc36e51b899e0a">/files/e81a0d8095d13664d7b01d6624fc36e51b899e0a</a></td><td><a href="/pages/c951a52fc64146dfb2f0971d93983ceb0e99eca7">/pages/c951a52fc64146dfb2f0971d93983ceb0e99eca7</a></td></tr><tr><td><strong>학습 결과</strong></td><td>완료된 학습 작업의 지표와 그래프를 검토하세요.</td><td><a href="/files/32fcde3dbc7ee8f7931c6714c55ef626f66bb8f2">/files/32fcde3dbc7ee8f7931c6714c55ef626f66bb8f2</a></td><td><a href="/pages/e80fe60ec34be1c2317321824e215ffbd5ae7412">/pages/e80fe60ec34be1c2317321824e215ffbd5ae7412</a></td></tr><tr><td><strong>학습된 모델 보기</strong></td><td>작업 공간에서 학습된 모델을 둘러보세요.</td><td><a href="/files/1720f32846609bea17fb179f6c0b97f813ec1318">/files/1720f32846609bea17fb179f6c0b97f813ec1318</a></td><td><a href="/pages/2e3c1bcfc3addcf4691b89433371caa21ec9612f">/pages/2e3c1bcfc3addcf4691b89433371caa21ec9612f</a></td></tr><tr><td><strong>학습 해상도</strong></td><td>각 모델 유형에 사용된 입력 해상도를 확인하세요.</td><td><a href="/files/895534a02bb0d111f5b3129e549ddfb4efc8dde0">/files/895534a02bb0d111f5b3129e549ddfb4efc8dde0</a></td><td><a href="/pages/1b0b7566b20740d9e5e8e14352fd589e3427c393">/pages/1b0b7566b20740d9e5e8e14352fd589e3427c393</a></td></tr><tr><td><strong>버전, 학습, 및 모델</strong></td><td>데이터셋, 학습 작업, 모델이 서로 어떻게 연관되는지.</td><td><a href="/files/aa1bd9c6c017921f8d1ccbc619ba31ddcdfdbdc8">/files/aa1bd9c6c017921f8d1ccbc619ba31ddcdfdbdc8</a></td><td><a href="/pages/e60ebb1cb5532092ac0d16fd0a0eacc3260df135">/pages/e60ebb1cb5532092ac0d16fd0a0eacc3260df135</a></td></tr><tr><td><strong>모델 ID</strong></td><td>배포하거나 추론을 실행할 때 모델이 어떻게 식별되는지.</td><td><a href="/files/6ff5b30f7a6d73d1ce1efe62829a031b94dcb2d0">/files/6ff5b30f7a6d73d1ce1efe62829a031b94dcb2d0</a></td><td><a href="/pages/069781d444c6eb8d397ad907c8cdd811e79bf334">/pages/069781d444c6eb8d397ad907c8cdd811e79bf334</a></td></tr></tbody></table>

학습된 모델은 다음을 통해 배포됩니다. [서버리스 API](https://docs.roboflow.com/deployment/roboflow-cloud/serverless-api), [전용 배포](https://docs.roboflow.com/deployment/roboflow-cloud/dedicated-deployments), 또는 [자체 호스팅 추론](https://docs.roboflow.com/deployment/self-hosted/self-hosted).