• torch ----------->>>>rknn


    Torch模型

    第一步:转换成onnx模型

    205服务器上,虚拟环境是py35_torch0.4.0

    /home/cbpm2016/temp

    生成my_net.onnx模型

    链接:https://pan.baidu.com/s/1nqk3vU-66iHrRJGLiDHBKQ
    提取码:gs5h
    复制这段内容后打开百度网盘手机App,操作更方便哦

    第二部:简化模型是在203 虚拟环境是liaolong_torch1.4

    /media/cbpm2016/D/wangj/pytorch/classifier/model_can_delete

    生成:output_onnx_model.onnx模型

    >> pip3 install onnx-simplifier
    >> python3 -m onnxsim input_model output_model

    第一步和第二部环境如下面

    第三步:转换成为ncnn模型

    150上自己编译的ncnn环境:torch1.4_py36_dc

    第三步:rknn模型

    203:/media/cbpm2016/E/lizeyuan/RKNN/rknn-toolkit/examples/onnx/unet


    absl-py 0.9.0
    addict 2.4.0
    albumentations 0.5.1
    astroid 2.4.2
    attrs 20.3.0
    backcall 0.2.0
    cachetools 4.1.1
    certifi 2020.6.20
    chardet 3.0.4
    cycler 0.10.0
    Cython 0.29.21
    dataclasses 0.6
    decorator 4.4.2
    dotty-dict 1.3.0
    easydict 1.9
    flake8 3.8.4
    flake8-import-order 0.18.1
    google-auth 1.19.2
    google-auth-oauthlib 0.4.1
    grpcio 1.30.0
    idna 2.10
    imageio 2.9.0
    imgaug 0.4.0
    importlib-metadata 1.7.0
    imutils 0.5.3
    iniconfig 1.1.1
    ipykernel 5.3.3
    ipython 7.16.1
    ipython-genutils 0.2.0
    isort 5.7.0
    jedi 0.17.1
    jupyter-client 6.1.6
    jupyter-core 4.6.3
    kiwisolver 1.2.0
    lazy-object-proxy 1.4.3
    Markdown 3.2.2
    matplotlib 3.3.0
    mccabe 0.6.1
    mkl-fft 1.1.0
    mkl-random 1.1.1
    mkl-service 2.3.0
    mmcls 0.7.0
    mmcv-full 1.2.6
    mmpycocotools 12.0.3
    mmtrack 0.5.0 /media/cbpm2016/E/duchao/pytorch/mmtracking
    MNN 1.1.2
    motmetrics 1.2.0
    networkx 2.5
    numpy 1.19.3
    oauthlib 3.1.0
    olefile 0.46
    onnx 1.6.0
    onnx-simplifier 0.3.2
    onnxoptimizer 0.2.3
    onnxruntime 1.6.0
    opencv-python-headless 4.4.0.46
    packaging 20.8
    pandas 1.0.5
    parso 0.7.0
    pexpect 4.8.0
    pickleshare 0.7.5
    Pillow 7.2.0
    pip 21.0.1
    pluggy 0.13.1
    prompt-toolkit 3.0.5
    protobuf 3.15.1
    ptyprocess 0.6.0
    py 1.10.0
    py-cpuinfo 7.0.0
    pyasn1 0.4.8
    pyasn1-modules 0.2.8
    pycocotools 2.0.1
    pycodestyle 2.6.0
    pyflakes 2.2.0
    Pygments 2.6.1
    pylint 2.6.0
    pyparsing 2.4.7
    pytest 6.2.1
    pytest-benchmark 3.2.3
    python-dateutil 2.8.1
    pytz 2020.1
    PyWavelets 1.1.1
    PyYAML 5.3.1
    pyzmq 19.0.1
    requests 2.24.0
    requests-oauthlib 1.3.0
    rsa 4.6
    scikit-image 0.17.2
    scipy 1.5.2
    seaborn 0.10.1
    setuptools 49.2.0.post20200714
    setuptools-scm 5.0.1
    Shapely 1.7.1
    six 1.15.0
    tensorboard 2.3.0
    tensorboard-plugin-wit 1.7.0
    terminaltables 3.1.0
    tifffile 2020.10.1
    toml 0.10.2
    torch 1.4.0
    torchvision 0.5.0
    tornado 6.0.4
    tqdm 4.48.0
    traitlets 4.3.3
    typed-ast 1.4.2
    typing-extensions 3.7.4.3
    urllib3 1.25.10
    wcwidth 0.2.5
    Werkzeug 1.0.1
    wheel 0.34.2
    wrapt 1.12.1
    xmltodict 0.12.0
    yapf 0.30.0
    zipp 3.1.0

  • 相关阅读:
    ASP.NET编程的十大技巧
    C#学习心得(转)
    POJ 1177 Picture (线段树)
    POJ 3067 Japan (树状数组)
    POJ 2828 Buy Tickets (线段树)
    POJ 1195 Mobile phones (二维树状数组)
    HDU 4235 Flowers (线段树)
    POJ 2886 Who Gets the Most Candies? (线段树)
    POJ 2418 Cows (树状数组)
    HDU 4339 Query (线段树)
  • 原文地址:https://www.cnblogs.com/shuimuqingyang/p/14460026.html
Copyright © 2020-2023  润新知