Question

我想使用MaskRCNN实现自定义图像分类器。

为了提高网络速度，我想优化推理。

我已经使用过OpenCV DNN库，但是我想在OpenVINO方面向前迈进一步。

我成功地使用OpenVINO模型优化器（python）构建了代表我的网络的.xml和.bin文件。

我使用Visual Studio 2017成功构建了OpenVINO Sample目录并运行MaskRCNNDemo项目。

mask_rcnn_demo.exe -m .\Release\frozen_inference_graph.xml -i .\Release\input.jpg

InferenceEngine:
        API version ............ 1.4
        Build .................. 19154
[ INFO ] Parsing input parameters
[ INFO ] Files were added: 1
[ INFO ]     .\Release\input.jpg
[ INFO ] Loading plugin

        API version ............ 1.5
        Build .................. win_20181005
        Description ....... MKLDNNPlugin
[ INFO ] Loading network files
[ INFO ] Preparing input blobs
[ WARNING ] Image is resized from (4288, 2848) to (800, 800)
[ INFO ] Batch size is 1
[ INFO ] Preparing output blobs
[ INFO ] Loading model to the plugin
[ INFO ] Start inference (1 iterations)

Average running time of one iteration: 2593.81 ms

[ INFO ] Processing output blobs
[ INFO ] Detected class 16 with probability 0.986519: [2043.3, 1104.9], [2412.87, 1436.52]
[ INFO ] Image out.png created!
[ INFO ] Execution successful

然后我尝试在一个单独的项目中重现此项目... 首先，我必须注意依赖关系...

<MaskRCNNDemo>
     //References
     <format_reader/>    => Open CV Images, resize it and get uchar data
     <ie_cpu_extension/> => CPU extension for un-managed layers (?)

     //Linker
     format_reader.lib         => Format Reader Lib (VINO Samples Compiled)
     cpu_extension.lib         => CPU extension Lib (VINO Samples Compiled)
     inference_engined.lib     => Inference Engine lib (VINO)
     opencv_world401d.lib      => OpenCV Lib
     libiomp5md.lib            => Dependancy
     ... (other libs)

使用它，我用自己的类和打开图像（多帧tiff）的方式构建了一个新项目。这项工作没有问题，那么我将不作介绍（我与CV DNN推理引擎一起使用没有问题）。

我想构建与MaskRCNNDemo相同的项目：CustomIA

<CustomIA>
     //References
     None => I use my own libtiff way to open image and i resize with OpenCV
     None => I will just add include to cpu_extension source code.

     //Linker
     opencv_world345d.lib   => OpenCV 3.4.5 library
     tiffd.lib              => Libtiff Library
     cpu_extension.lib      => CPU extension compiled with sample
     inference_engined.lib  => Inference engine lib.

我在项目目标目录中添加了以下dll：

cpu_extension.dll
inference_engined.dll
libiomp5md.dll
mkl_tiny_omp.dll
MKLDNNPlugind.dll
opencv_world345d.dll
tiffd.dll
tiffxxd.dll

我成功地编译并执行了，但是遇到两个问题：

旧代码：

 slog::info << "Loading plugin" << slog::endl;
    InferencePlugin plugin = PluginDispatcher({ FLAGS_pp, "../../../lib/intel64" , "" }).getPluginByDevice(FLAGS_d);

    /** Loading default extensions **/
    if (FLAGS_d.find("CPU") != std::string::npos) {
        /**
         * cpu_extensions library is compiled from "extension" folder containing
         * custom MKLDNNPlugin layer implementations. These layers are not supported
         * by mkldnn, but they can be useful for inferring custom topologies.
        **/
        plugin.AddExtension(std::make_shared<Extensions::Cpu::CpuExtensions>());
    }
    /** Printing plugin version **/
    printPluginVersion(plugin, std::cout);

输出：

[ INFO ] Loading plugin
    API version ............ 1.5
    Build .................. win_20181005
    Description ....... MKLDNNPlugin

新代码：

    VINOEngine::VINOEngine()
{
    // Loading Plugin
    std::cout << std::endl;
    std::cout << "[INFO] - Loading VINO Plugin..." << std::endl;
    this->plugin= PluginDispatcher({ "", "../../../lib/intel64" , "" }).getPluginByDevice("CPU");
    this->plugin.AddExtension(std::make_shared<Extensions::Cpu::CpuExtensions>());
    printPluginVersion(this->plugin, std::cout);

输出：

[INFO] - Loading VINO Plugin...
000001A242280A18  // Like memory adress ???

第二期：

当我尝试从新代码中提取投资回报率和蒙版时，如果我有一个“匹配项”，我总是会：

得分= 1.0
x1 = x2 = 0.0
y1 = y2 = 1.0

但是面具看起来很好提取...

新代码：

        float score = box_info[2];
        if (score > this->Conf_Threshold)
        {
            // On reconstruit les coordonnées de la box..
            float x1 = std::min(std::max(0.0f, box_info[3] * Image.cols), static_cast<float>(Image.cols));
            float y1 = std::min(std::max(0.0f, box_info[4] * Image.rows), static_cast<float>(Image.rows));
            float x2 = std::min(std::max(0.0f, box_info[5] * Image.cols), static_cast<float>(Image.cols));
            float y2 = std::min(std::max(0.0f, box_info[6] * Image.rows), static_cast<float>(Image.rows));
            int box_width = std::min(static_cast<int>(std::max(0.0f, x2 - x1)), Image.cols);
            int box_height = std::min(static_cast<int>(std::max(0.0f, y2 - y1)), Image.rows);

Image is resized from (4288, 2848) to (800, 800)
Detected class 62 with probability 1: [4288, 0], [4288, 0]

然后，当我没有正确的bbox坐标时，我不可能将遮罩放置在图像中并调整其大小...

有人对我做得不好有想法吗？

如何使用cpu_extension创建和正确链接OpenVINO项目？

谢谢！

Answer 1

版本的第一个问题：在printPluginVersion函数上方，您将看到InferenceEngine和插件版本信息的重载std :: ostream运算符。

第二：您可以尝试通过比较原始卷积和原始层和OV的输出层后的输出来调试模型。确保每个元素都相等。

在OV中，您可以使用network.addOutput（“ layer_name”）将任何图层添加到输出中。然后使用以下命令读取输出：const Blob :: Ptr debug_blob = infer_request.GetBlob（“ layer_name”）。

在大多数情况下，我会发现缺少输入预处理（均值，规范化等）

cpu_extensions是一个动态库，但您仍然可以更改cmake脚本以使其静态并与应用程序链接。之后，您将需要使用应用程序路径来调用IExtensionPtr extension_ptr = make_so_pointer（argv [0]）

遮罩RCNN OpenVino-C ++ API

1 个答案: