跳到主要内容

ConvNext-Tiny 示例

此文档讲述使用 QAI AppBuilder Python API 利用 Qualcomm® Hexagon™ Processor (NPU) 推理 ConvNext-Tiny 目标识别模型。

示例支持设备

设备SoC
Dragon Q6AQCS6490
Dragon Q8BSC8280XP

安装 QAI AppBuilder

提示
  1. 请根据 QAI AppBuilder 安装方法 安装 QAI AppBuilder。

  2. 请根据 配置 QAIRT 环境变量 配置 QAIRT 环境变量。

运行示例

安装依赖

Device
pip3 install requests tqdm qai-hub py3_wget opencv-python torch torchvision

运行脚本

  • 进入示例目录

    Device
    cd ai-engine-direct-helper/samples/linux/python
  • 准备输入图片,这里以以下图片为输入示例

    input image

  • 执行推理

    Device
    python3 convnext_tiny/convnext_tiny.py
    $ python3 convnext_tiny/convnext_tiny.py
    Current file directory: /mnt/ssd/qualcomm/701/zzf_fork/ai-engine-direct-helper/samples/linux/python/convnext_tiny
    0.0ms [WARNING] <W> Initializing HtpProvider

    /prj/qct/webtech_scratch20/mlg_user_admin/qaisw_source_repo/rel/qairt-2.37.1/point_release/SNPE_SRC/avante-tools/prebuilt/dsp/hexagon-sdk-5.4.0/ipc/fastrpc/rpcmem/src/rpcmem_android.c:38:dummy call to rpcmem_init, rpcmem APIs will be used from libxdsprpc
    0.0ms [WARNING] <W> This META does not have Alloc2 Support

    0.0ms [WARNING] <W> This META does not have Alloc2 Support

    0.0ms [WARNING] <W> This META does not have Alloc2 Support

    0.0ms [WARNING] <W> This META does not have Alloc2 Support

    132.1ms [WARNING] Time: Read model file to memory. 15.88

    0.0ms [WARNING] <W> This META does not have Alloc2 Support

    0.0ms [WARNING] <W> This META does not have Alloc2 Support

    0.0ms [WARNING] <W> This META does not have Alloc2 Support

    0.0ms [WARNING] <W> This META does not have Alloc2 Support

    0.0ms [WARNING] <W> This META does not have Alloc2 Support

    0.0ms [WARNING] <W> This META does not have Alloc2 Support

    0.0ms [WARNING] <W> This META does not have Alloc2 Support

    176.1ms [WARNING] Time: contextCreateFromBinary. 44.01

    176.2ms [WARNING] Time: UnmapViewOfFile. 0.00

    176.6ms [WARNING] Time: model_initialize convnext_tiny 176.53

    245.2ms [WARNING] Time: model_inference convnext_tiny 11.95

    Top 5 predictions for image:

    Samoyed 0.637629509
    Pomeranian 0.1382825226
    keeshond 0.0217001885
    Arctic fox 0.0138142202
    white wolf 0.0115938596
    0.0ms [WARNING] <W> This META does not have Alloc2 Support

    0.0ms [WARNING] <W> This META does not have Alloc2 Support

    0.0ms [WARNING] <W> This META does not have Alloc2 Support

    0.0ms [WARNING] <W> This META does not have Alloc2 Support

    /prj/qct/webtech_scratch20/mlg_user_admin/qaisw_source_repo/rel/qairt-2.37.1/point_release/SNPE_SRC/avante-tools/prebuilt/dsp/hexagon-sdk-5.4.0/ipc/fastrpc/rpcmem/src/rpcmem_android.c:42:dummy call to rpcmem_deinit, rpcmem APIs will be used from libxdsprpc
    263.1ms [WARNING] Time: model_destroy convnext_tiny 15.29

    打印结果可以看到 Samoyed 置信度最高,这与输入图片内容吻合。

    您需要登录 GitHub 才能发表评论。如果您已登录,请忽略此消息。

    Radxa-docs © 2026 by Radxa Computer (Shenzhen) Co.,Ltd. is licensed under CC BY 4.0