# AI Hub를 설정하여 AI 모델 최적화

Qualcomm AI 하드웨어에서 모델의 프로토타입을 빠르게 생성할 수 있도록 AI Hub는 비전, 오디오, 음성 사용 사례에 맞게 기기에서 머신 러닝 모델을 최적화, 검증, 배포하는 방법을 제공합니다.

![../_images/ai-hub_QLI.png](data:image/png;base64,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)

## 환경 설정

1. Python 환경을 설정합니다. 컴퓨터에 [miniconda](https://docs.conda.io/projects/miniconda/en/latest/miniconda-install.html) 를 설치합니다.

Tab Windows
Tab macOS/Linux

설치가 완료되면 Start(시작) 메뉴에서 Anaconda 프롬프트를 엽니다.

설치가 완료되면 새로운 셸 창을 엽니다.

    AI Hub의 Python 가상 환경을 설정합니다.

conda activate
        Copy to clipboard

conda create python=3.10 -n qai_hub
        Copy to clipboard

conda activate qai_hub
        Copy to clipboard
2. git을 설치합니다.

sudo apt-get install git
        Copy to clipboard
3. AI Hub Python 클라이언트를 설치합니다.

pip3 install qai-hub
        Copy to clipboard

pip3 install "qai-hub[torch]"
        Copy to clipboard
4. AI Hub에 로그인합니다.

    [AI Hub](https://aihub.qualcomm.com/) 로 이동하고 Qualcomm ID로 로그인하여 생성한 작업에 대한 정보를 확인합니다.

    로그인되면 *Account(계정) &gt; Settings(설정) &gt; API Token(API 토큰)* 으로 이동합니다. 그러면 클라이언트를 구성하는 데 사용할 수 있는 API 토큰이 제공됩니다.
5. 다음 명령어를 터미널에 입력하여 API 토큰으로 클라이언트를 구성하세요.

qai-hub configure --api_token <INSERT_API_TOKEN>
        Copy to clipboard

## AI Hub 워크플로우 선택

### 사전 최적화된 모델 사용해 보기

1. [AI Hub Model Zoo](https://aihub.qualcomm.com/iot/models) 로 이동하여 Qualcomm 평가 키트에 사용할 수 있는 사전 최적화된 모델에 접근합니다.
2. EVK에 사용할 수 있는 모델을 필터링합니다. 예를 들어 왼쪽 창에서 *Qualcomm QCS6490* 을 칩셋으로 선택하여 Qualcomm Dragonwing™ RB3 Gen 2에 사전 최적화된 모델을 다운로드할 수 있습니다.
3. 필터링된 보기에서 모델을 선택하여 모델 페이지로 이동합니다.
4. 모델 페이지의 드롭다운 목록에서 칩셋을 선택하고 *TorchScript &gt; LiteRT* 경로를 선택합니다.
5. 다운로드를 선택하여 모델 다운로드를 시작합니다. 다운로드한 모델은 사전 최적화되어 배포 준비를 마친 상태입니다. 모델 배포에 대한 자세한 내용은 [자체 AI/ML 애플리케이션 개발](https://docs.qualcomm.com/doc/80-70020-15BK/topic/develop-your-own-application.html) 을 참조하세요.

![../_images/ai-hub-download.png](data:image/png;base64,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)

### 자체 모델 가져오기

1. PyTorch 또는 ONNX 형식의 사전 학습된 모델을 선택합니다.
2. python API를 사용하여 컴파일 또는 최적화할 모델을 AI Hub에 제출합니다.

    컴파일 작업을 제출할 때 반드시 EVK용 기기 또는 칩셋과 모델을 컴파일할 타겟 런타임을 선택해야 합니다. RB3Gen2의 경우 LiteRT 런타임이 지원됩니다.

    | **칩셋** | **런타임** | **CPU** | **GPU** | **HTP** |
    | --- | --- | --- | --- | --- |
    | Qualcomm Dragonwing™ RB3 Gen 2 | LiteRT | INT8, FP16, FP32 | FP16, FP32 | INT8, INT16 |

    제출하면 AI Hub에서 작업의 고유 ID가 생성됩니다. 이 작업 ID를 사용하여 작업 세부 정보를 확인할 수 있습니다.
3. AI Hub는 선택한 기기와 런타임에 기반하여 모델을 최적화합니다.

    - 선택 사항으로, 기기 팜에서 프로비저닝된 실제 기기에서 Python API를 사용하여 최적화된 모델을 프로파일링하거나 추론하는 작업을 제출할 수 있습니다.

        - 프로파일링: 프로비저닝된 기기에서 모델을 벤치마크하고, 레이어 수준의 평균 추론 시간, 런타임 구성 등을 포함한 통계를 제공합니다.
        - 추론: 프로비저닝된 기기에서 모델을 실행하여 추론 작업에 제출된 데이터에 대해 최적화된 모델을 사용하여 추론을 수행합니다.
4. 제출된 각 작업은 AI Hub 포털에서 검토할 수 있습니다. 제출된 컴파일 작업은 최적화된 모델을 다운로드할 수 있는 링크를 제공합니다. 그러면 이 최적화된 모델을 RB3Gen2와 같은 로컬 개발 기기에 배포할 수 있습니다.

다음은 설명한 워크플로우의 예시로, [AI Hub 문서](https://app.aihub.qualcomm.com/docs/) 에서 가져온 것입니다. 이 예시에서는 PyTorch의 사전 학습된 모델 MobileNet V2를 AI Hub에 업로드하고, 최적화된 LiteRT 모델로 컴파일하여 RB3Gen2 타겟에서 실행합니다.

import qai_hub as hub
    import torch
    from torchvision.models import mobilenet_v2
    import numpy as np
    
    # Using pre-trained MobileNet
    torch_model = mobilenet_v2(pretrained=True)
    torch_model.eval()
    
    # Trace model (for on-device deployment)
    input_shape = (1, 3, 224, 224)
    example_input = torch.rand(input_shape)
    traced_torch_model = torch.jit.trace(torch_model, example_input)
    
    # Compile and optimize the model for a specific device
    compile_job = hub.submit_compile_job(
        model=traced_torch_model,
        device=hub.Device("QCS6490 (Proxy)"),
        input_specs=dict(image=input_shape),
        #compile_options="--target_runtime tflite",
    )
    
    # Profiling Job
    profile_job = hub.submit_profile_job(
        model=compile_job.get_target_model(),
        device=hub.Device("QCS6490 (Proxy)"),
    )
    
    sample = np.random.random((1, 3, 224, 224)).astype(np.float32)
    
    # Inference Job
    inference_job = hub.submit_inference_job(
        model=compile_job.get_target_model(),
        device=hub.Device("QCS6490 (Proxy)"),
        inputs=dict(image=[sample]),
    )
    
    # Download model
    compile_job.download_target_model(filename="/tmp/mobilenetv2.tflite")
    Copy to clipboard

참고

이전에 활성화된 `qai_hub` 환경을 비활성화하려면 다음 명령어를 사용하세요.

conda deactivate
    Copy to clipboard

모델이 다운로드되면 [자체 AI/ML 애플리케이션 개발](https://docs.qualcomm.com/doc/80-70020-15BK/topic/develop-your-own-application.html) 에 사용할 수 있습니다.

AI Hub 워크플로우 및 API에 대한 자세한 내용은 [AI Hub 문서](https://app.aihub.qualcomm.com/docs/hub/index.html#examples) 를 참조하거나, [AI Hub 튜토리얼 비디오](https://www.youtube.com/watch?v=V1CDWYZ7Shw&amp;list=PLxeazpXYyqtOowtUdvigvAgMV5_K1KIrh) 를 살펴보거나, AI Hub에서 모델을 프로파일링하는 방법에 대한 다음 비디오를 시청하세요.

<svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" viewbox="0 0 800 500" width="800" height="500" style="cursor:auto !important" aria-label="../_images/ai-hub-video.svg" svgdefaultwidth="75%">
    <defs>
      <style>@import url("https://fonts.googleapis.com/css2?family=Roboto+Flex:opsz,wght@8..144,100..1000&amp;display=swap");
.svg-1 .bg-fill { fill: var(--color-background) }
.svg-1 .fill-text { color: var(--color-content); fill: var(--color-content) }
.svg-1 .video-hoverbox { transition: opacity 0.15s ease-in-out }
.svg-1 .video-hoverbox:hover { opacity: 0.9 }</style>
  </defs>

  <foreignobject x="0" y="0" width="800" height="500">
    <body xmlns="http://www.w3.org/1999/xhtml">
        <iframe width="800" height="500" src="https://players.brightcove.net/1414329538001/4JiZQnWhg_default/index.html?videoId=6366848482112" allowfullscreen="" allow="encrypted-media"></iframe>
    <div class='topic-detail'><div class='topic-updated-date'><span> Last Published: </span>Dec 23, 2025</div><div class='prev-and-next-links'><span class='previous-topic-link'><span aria-hidden='true' class='disabled' data-tip='' data-effect='solid'></span></span></div></div></body>
    </foreignobject>
</svg>

참고

위의 비디오에서는 Python 3.8을 예시로 사용합니다.

Python 3.8과 Python 3.10이 지원됩니다.

Last Published: Dec 23, 2025

[Previous Topic
AI 모델 컴파일 및 최적화](https://docs.qualcomm.com/bundle/publicresource/80-70020-15BK/topics/compile-and-optimize-model.md) [Next Topic
LiteRT를 사용하여 AI 모델 최적화](https://docs.qualcomm.com/bundle/publicresource/80-70020-15BK/topics/tflite.md)