# 在应用程序中集成 AI Hub 模型 本节介绍如何在参考应用程序中使用 AI Hub 模型。此示例使用来自 AI Hub 的图像分类模型。 Note 大多数公开的图像分类模型的预处理和后处理都类似，并且可能由 `qtimlvclassification` 插件支持。 Qualcomm AI Hub 为 Qualcomm 设备提供优化的 AI 模型，允许它们使用 LiteRT（以前称为 Tensorflow Lite）或Qualcomm® AI Engine Direct 在 CPU、GPU 或 NPU 上运行。 此示例说明如何使用 AI Hub 中的 [mobilenet-v2](https://aihub.qualcomm.com/iot/models/mobilenet_v2) 模型并将该模型集成到 `gst-ai-classification` 参考应用程序中。 | **编号** | **示例程序** | **经过验证的 AI Hub 模型** | **标签文件** | | --- | --- | --- | --- | | 1 | gst-ai-classification | GoogleNet: | [标签](https://github.com/quic/sample-apps-for-qualcomm-linux/blob/main/artifacts/labels/classification.labels) | | 2 | gst-ai-classification | inception\_v3 | [标签](https://github.com/quic/sample-apps-for-qualcomm-linux/blob/main/artifacts/labels/classification.labels) | | 3 | gst-ai-classification | mobilenet-v2 | [标签](https://github.com/quic/sample-apps-for-qualcomm-linux/blob/main/artifacts/labels/classification.labels) | | 4 | gst-ai-classification | MobileNet-v3-Large | [标签](https://github.com/quic/sample-apps-for-qualcomm-linux/blob/main/artifacts/labels/classification.labels) | | 5 | gst-ai-classification | ResNet101 | [标签](https://github.com/quic/sample-apps-for-qualcomm-linux/blob/main/artifacts/labels/classification.labels) | | 6 | gst-ai-classification | SqueezeNet-1\_1 | [标签](https://github.com/quic/sample-apps-for-qualcomm-linux/blob/main/artifacts/labels/classification.labels) | | 7 | gst-ai-classification | ResNet18 | [标签](https://github.com/quic/sample-apps-for-qualcomm-linux/blob/main/artifacts/labels/classification.labels) | | 8 | gst-ai-classification | ResNeXt50 | [标签](https://github.com/quic/sample-apps-for-qualcomm-linux/blob/main/artifacts/labels/classification.labels) | | 9 | gst-ai-classification | WideResNet50 | [标签](https://github.com/quic/sample-apps-for-qualcomm-linux/blob/main/artifacts/labels/classification.labels) | | 10 | gst-ai-classification | Shufflenet-v2 | [标签](https://github.com/quic/sample-apps-for-qualcomm-linux/blob/main/artifacts/labels/classification.labels) | | 11 | gst-ai-classification | ResNeXt101 | [标签](https://github.com/quic/sample-apps-for-qualcomm-linux/blob/main/artifacts/labels/classification.labels) | | 12 | gst-ai-segmentation | deeplabv3\_plus\_mobilenet | [标签](https://github.com/quic/sample-apps-for-qualcomm-linux/blob/main/artifacts/labels/deeplabv3_resnet50.labels) | | 13 | gst-ai-segmentation | [fcn\_](https://docs.qualcomm.com/doc/80-70020-15BY/topic/integrate-ai-hub-models.html#id6) resnet50 | [标签](https://github.com/quic/sample-apps-for-qualcomm-linux/blob/main/artifacts/labels/deeplabv3_resnet50.labels) | | 14 | gst-ai-segmentation | ffnet\_40s | [标签](https://github.com/quic/sample-apps-for-qualcomm-linux/blob/main/artifacts/labels/deeplabv3_resnet50.labels) | | 15 | gst-ai-segmentation | ffnet\_54s | [标签](https://github.com/quic/sample-apps-for-qualcomm-linux/blob/main/artifacts/labels/deeplabv3_resnet50.labels) | | 16 | gst-ai-segmentation | ffnet\_78s | [标签](https://github.com/quic/sample-apps-for-qualcomm-linux/blob/main/artifacts/labels/deeplabv3_resnet50.labels) | | 17 | gst-ai-object-detection | Yolo-v7 | [标签](https://github.com/quic/sample-apps-for-qualcomm-linux/blob/main/artifacts/labels/detection.labels) | | 18 | gst-ai-object-detection | YOLOv8-Detection | [标签](https://github.com/quic/sample-apps-for-qualcomm-linux/blob/main/artifacts/labels/detection.labels) | | 19 | GST-AI-superresolution | QuickSRNetLarge | 不适用 | | 20 | GST-AI-superresolution | QuickSRNetMedium | 不适用 | | 21 | GST-AI-superresolution | QuickSRNetSmall | 不适用 | | 22 | GST-AI-superresolution | XLSR | 不适用 | | 23 | gst-ai-monodepth | Midas-V2 | [标签](https://github.com/quic/sample-apps-for-qualcomm-linux/blob/main/artifacts/labels/monodepth.labels) | | 24 | gst-ai-pose-detection | HRNetPose | [标签](https://github.com/quic/sample-apps-for-qualcomm-linux/blob/main/artifacts/labels/hrnet_pose.labels) | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Note 某些模型在 AI Hub 上只有 LiteRT 或 Qualcomm AI Engine Direct SDK 模型。不过，AI Hub 经常更新其中的库以包含更多模型并增强现有模型。 前提条件 1. 下载 [AI Hub 模型](https://aihub.qualcomm.com/iot/models)。 2. 选择要下载其模型的 Chipset 。 - 对于 Qualcomm Dragonwing™ RB3 Gen 2，选择 *Qualcomm QCS6490* - 对于 QCS9075，选择 *Qualcomm QCS9075* - 对于 QCS8275，选择 *Qualcomm QCS8275* 3. 将与型号匹配的标签文件复制到设备。 标签文件可通过提供的[链接](https://github.com/quic/ai-hub-models/tree/main/qai_hub_models/labels)下载。 Note 以下部分使用占位符模型名称来表示通过 AI Hub 下载的模型。使用通过 AI Hub 下载的适当模型名称更新命令中的模型名称。 ## 获取模型常数 1. 使用图查看器工具（如 [Netron](https://netron.app/)）打开下载的 LiteRT 模型。 2. 检查特定模型的后处理要求，将其包含在参考应用程序中。 1. 点击模型的输入节点可查看模型属性。 2. 复制模型输出节点的值。 ![../_images/execute-mobilenet-v2-model-properties.png](data:image/png;base64,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) 例如，在上图中，`q_scale` 是 quantization: linear 中提到的值，`q_offset` 输出的值为 `-59`。您需要更改基于插件实现需要的模型图中 `q_offset` 的符号。 请您记下这些值并在修改配置时使用它们。 ## 修改配置 1. 将模型复制到设备。 scp mobilenet_v2_quantized.tflite root@:/etc/models/ Copy to clipboard 2. 将标签复制到设备。 wget https://raw.githubusercontent.com/quic/ai-hub-models/refs/heads/main/qai_hub_models/labels/imagenet_labels.txt Copy to clipboard scp imagenet_labels.txt root@:/etc/labels/ Copy to clipboard 3. 更新 `/etc/configs/config_classification.json` 文件，如下所示。 { "file-path": "/etc/media/video.mp4", "ml-framework": "tflite", "model": "/etc/models/mobilenet_v2_quantized.tflite", "labels": "/etc/labels/imagenet_labels.txt", "constants": "Mobilenet,q-offsets=<63.0>,q-scales=<0.16931529343128204>;", "threshold": 40, "runtime": "dsp" } Copy to clipboard Note 使用 [获取模型常数](https://docs.qualcomm.com/doc/80-70020-15BY/topic/integrate-ai-hub-models.html#get-model-constants) 中注明的值更新 `q_offset` 和 `q_scale` 。 ## 运行示例应用程序 1. 运行以下命令，为显示器启用 Weston 服务： export XDG_RUNTIME_DIR=/dev/socket/weston && export WAYLAND_DISPLAY=wayland-1 Copy to clipboard 2. 在命令行参数中指定常量值，运行示例程序： gst-ai-classification --config-file=/etc/configs/config_classification.json Copy to clipboard 3. 使用示例应用程序在用户的设备上运行各种 AI Hub 模型。运行不同的 AI Hub 模型： 1. 下载您想要运行的模型和标签文件。 2. 将模型和标签文件复制到设备。 3. 使用 [Netron](https://netron.app/) 应用程序检查模型文件，相应地填写常量参数。 按照以下步骤运行示例应用程序。 Tab gst-ai-object-detection Tab gst-ai-segmentation Tab gst-ai-superresolution 1. 按照[中的步骤下载模型文件](https://docs.qualcomm.com/doc/80-70020-15BY/topic/classify-objects-with-default-model.html#download-model-files)以获取 YOLOv8 Quantized LiteRT 模型文件（用于对象检测）。 2. 更新 `/etc/configs/config_detection.json` 文件，如下所示。 { "file-path": "/etc/media/video.mp4", "ml-framework": "tflite", "yolo-model-type": "yolov8", "model": "/etc/models/yolov8_det_quantized.tflite", "labels": "/etc/labels/yolonas.labels", "constants": "YOLOv8,q-offsets=<21.0, 0.0, 0.0>,q-scales=<3.093529462814331, 0.00390625, 1.0>;", "threshold": 40, "runtime": "dsp" } Copy to clipboard Note 根据用户获取到的模型，更新配置文件中的模型名称和模型常量。 3. 运行示例应用程序。 Note 确保您已将模型和标签文件复制至设备。 gst-ai-object-detection --config-file=/etc/configs/config_detection.json Copy to clipboard 1. 更新 `/etc/configs/config_segmentation.json` 文件如下： 使用 `deeplabv3_plus_mobilenet_quantized.tflite` 模型文件（用于分割）和 `deeplabv3_resnet50.labels` 文件作为示例。 { "file-path": "/etc/media/video.mp4", "ml-framework": "tflite", "model": "/etc/models/deeplabv3_plus_mobilenet_quantized.tflite", "labels": "/etc/labels/deeplabv3_resnet50.labels", "constants": "deeplab,q-offsets=<0.0>,q-scales=<1.0>;", "runtime": "dsp" } Copy to clipboard 2. 运行示例应用程序。 gst-ai-segmentation --config-file=/etc/configs/config_segmentation.json Copy to clipboard 1. 更新 `/etc/configs/config-superresolution.json` 文件，如下所示。 { "input-file-path": "/etc/media/super.mp4", "model": "/etc/models/quicksrnetsmall_quantized.tflite", "constants": "srnet,q-offsets=<0.0>,q-scales=<1.0>;", "output-file-path":"/etc/media/out.mp4" } Copy to clipboard 2. 运行示例应用： gst-ai-superresolution --config-file=/etc/configs/config-superresolution.json Copy to clipboard Note 确保使用的视频具有 128x128 分辨率，作为模型的输入。 关于输入参数的更多详细信息，请参阅应用程序的帮助部分。 Note 在进行分割的情况下，未被识别的对象可能会以白色背景显示。该问题源于标签文件，将在未来的更新中得到解决。 4. 如需进行任何更改，可重新编译示例程序并运行。有关如何使用 eSDK 编译参考应用程序的说明，请参阅 [Qualcomm Intelligent Multimedia 软件开发包 (IM SDK) 快速入门指南](https://docs.qualcomm.com/bundle/publicresource/topics/80-70020-51/introduction.html)。 Last Published: Oct 12, 2025 [Previous Topic 在应用程序中集成定制AI模型](https://docs.qualcomm.com/bundle/publicresource/80-70020-15BY/topics/integrate-custom-model.md) [Next Topic 为定制模型添加后处理支持](https://docs.qualcomm.com/bundle/publicresource/80-70020-15BY/topics/add-postprocessing-support-custom-model.md) Source: [https://docs.qualcomm.com/doc/80-70020-15BY/topic/integrate-ai-hub-models.html](https://docs.qualcomm.com/doc/80-70020-15BY/topic/integrate-ai-hub-models.html)