# 偵測對象

在運行模型的管道命令之前，請遵循必要的 [先決條件](https://docs.qualcomm.com/doc/80-70018-15BT/topic/ai-hub-qualcomm-im-sdk.html#prerequisites)。

運行以下命令以確保結果顯示在連接的顯示器上。

export XDG_RUNTIME_DIR=/dev/socket/weston && export WAYLAND_DISPLAY=wayland-1
    Copy to clipboard

## Yolo-V7 量化

YoloV7是一種機器學習模型，可以預測圖像中對象的邊界框和類別。

該模型使用COCO數據集中的樣本進行訓練後量化為int8。

AI Hub模型基於 [Yolo-v7-Quantized的實現](https://github.com/WongKinYiu/yolov7/) 。

- 模型：[Yolo-v7-Quantized.tflite](https://aihub.qualcomm.com/iot/models/yolov7_quantized)
- 標籤：[coco_labels.txt](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/labels/coco_labels.txt)

gst-launch-1.0 -e --gst-debug=2 \
    filesrc location=/etc/media/video.mp4 ! qtdemux ! queue ! h264parse ! v4l2h264dec capture-io-mode=4 output-io-mode=4 ! video/x-raw,format=NV12 ! queue ! tee name=split \
    split. ! queue ! qtivcomposer name=mixer ! queue ! waylandsink fullscreen=true \
    split. ! queue ! qtimlvconverter ! queue ! qtimltflite delegate=external external-delegate-path=libQnnTFLiteDelegate.so \
    external-delegate-options="QNNExternalDelegate,backend_type=htp;" model=/etc/models/Yolo-v7-Quantized.tflite ! queue ! \
    qtimlvdetection threshold=50.0 results=10 module=yolov8 labels=/etc/labels/coco_labels.txt constants="YOLOv7,q-offsets=<35.0, 0.0, 0.0>,q-scales=<3.4220554, 0.0023370725102722645, 1.0>;" ! \
    video/x-raw,format=BGRA,width=640,height=360 ! queue ! mixer.
    Copy to clipboard

## Yolov8-Detection-Quantized

Ultralytics Yolov8是一種機器學習模型，可以預測圖像中對象的邊界框和類別。

該模型使用COCO數據集中的樣本進行訓練後量化為int8。

AI Hub模型基於 [YOLOv8-Detection-Quantized的實現](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/models/yolo/detect) 。

- 模型： [YOLOv8-Detection-Quantized.tflite](https://aihub.qualcomm.com/iot/models/yolov8_det_quantized)
- 標籤：[coco_labels.txt](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/labels/coco_labels.txt)

gst-launch-1.0 -e --gst-debug=2 \
    filesrc location=/etc/media/video.mp4 ! qtdemux ! queue ! h264parse ! v4l2h264dec capture-io-mode=4 output-io-mode=4 ! video/x-raw,format=NV12 ! queue ! tee name=split \
    split. ! queue ! qtivcomposer name=mixer ! queue ! waylandsink fullscreen=true \
    split. ! queue ! qtimlvconverter ! queue ! qtimltflite delegate=external external-delegate-path=libQnnTFLiteDelegate.so \
    external-delegate-options="QNNExternalDelegate,backend_type=htp,htp_device_id=(string)0,htp_performance_mode=(string)2,htp_precision=(string)1;" model=/etc/models/YOLOv8-Detection-Quantized.tflite ! queue ! \
    qtimlvdetection threshold=50.0 results=10 module=yolov8 labels=/etc/labels/coco_labels.txt constants="YOLOv8,q-offsets=<21.0, 0.0, 0.0>,q-scales=<3.093529462814331, 0.00390625, 1.0>;" ! \
    video/x-raw,format=BGRA,width=640,height=360 ! queue ! mixer.
    Copy to clipboard

備註

在上述命令中添加 `htp_device_id=(string)0,htp_performance_mode=(string)2,htp_precision=(string)1` 到 `external-delegate-options` ，允許模型在HTP上以高性能模式運行。

可以以相同的方式為所有其他管道啟用高性能模式。

## Yolo-nas-Quantized

YoloNAS是一種機器學習模型，可以預測圖像中對象的邊界框和類別。

該模型使用COCO數據集中的樣本進行訓練後量化為int8。

AI Hub模型基於 [Yolo-nas-Quantized的實現](https://github.com/Deci-AI/super-gradients)  。

- 模型：[Yolo-NAS-Quantized.tflite](https://aihub.qualcomm.com/iot/models/yolonas_quantized)
- 標籤：[coco_labels.txt](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/labels/coco_labels.txt)

gst-launch-1.0 -e --gst-debug=2 \
    filesrc location=/etc/media/video.mp4 ! qtdemux ! queue ! h264parse ! v4l2h264dec capture-io-mode=4 output-io-mode=4 ! video/x-raw,format=NV12 ! queue ! tee name=split \
    split. ! queue ! qtivcomposer name=mixer ! queue ! waylandsink fullscreen=true \
    split. ! queue ! qtimlvconverter ! queue ! qtimltflite delegate=external external-delegate-path=libQnnTFLiteDelegate.so \
    external-delegate-options="QNNExternalDelegate,backend_type=htp;" model=/etc/models/Yolo-NAS-Quantized.tflite ! queue ! \
    qtimlvdetection threshold=50.0 results=10 module=yolov8 labels=/etc/labels/coco_labels.txt constants="yolo-nas,q-offsets=<37.0,0.0, 0.0>,q-scales=<3.416602611541748, 0.00390625, 1.0>;" ! \
    video/x-raw,format=BGRA,width=640,height=360 ! queue ! mixer.
    Copy to clipboard

Last Published: Oct 15, 2025

[Previous Topic
圖像分類](https://docs.qualcomm.com/bundle/publicresource/80-70018-15BT/topics/image-classification.md) [Next Topic
對影片幀應用語義分割](https://docs.qualcomm.com/bundle/publicresource/80-70018-15BT/topics/semantic-segmentation.md)