如何使用 Opencv dnn 模块调用 Caffe 预训练模型？

 QString modelPrototxt = "D:\\Qt\\qmake\\CaffeModelTest\\caffe\\lenet.prototxt";
    QString modelBin = "D:\\Qt\\qmake\\CaffeModelTest\\caffe\\snapshot_iter_10000.caffemodel";
    QString imageFile = "D:\\Qt\\qmake\\CaffeModelTest\\caffe\\9.png";

    //读取存储在caffe模型文件中的网络模型
    cv::dnn::Net net = cv::dnn::readNetFromCaffe(modelPrototxt.toStdString(),modelBin.toStdString());
    if (net.empty())
    {
        qDebug() << "readNetFromCaffe faild";
    }

    //读取图像文件
    cv::Mat img = cv::imread(imageFile.toStdString(),0);
    if(img.empty())
    {
        qDebug() << "imread faild";
    }

    cv::Mat inputBlob = cv::dnn::blobFromImage(img,0.00390625f, cv::Size(28, 28), cv::Scalar(), false);
    cv::Mat prob;
    cv::TickMeter t;
    for (int i = 0; i < 1; i++)
    {
        //设置网络的输入层名字（和训练网络模型文件里面的 name 对应）
        net.setInput(inputBlob, "data");
        t.start();
        //设置网络的输出层名字（和训练网络模型文件里面的 name 对应）
        prob = net.forward("prob");
        t.stop();
    }

    int classId;
    double classProb;
    cv::Mat probMat = prob.reshape(1, 1); //reshape the blob to 1x1000 matrix
    cv::Point classNumber;

    cv::minMaxLoc(probMat, NULL, &classProb, NULL, &classNumber);
    classId = classNumber.x;

    qDebug() << t.getTimeMicro() << "index:" << classId << "%"<< classProb;

LeNet

name: "LeNet"
input: "data"
input_shape {
  dim: 1   # batchsize
  dim: 1   # number of channels
  dim: 28  # width
  dim: 28  # height
}
layer {
  name: "conv1"
  type: "Convolution"
  bottom: "data"
  top: "conv1"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  convolution_param {
    num_output: 20
    kernel_size: 5
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "pool1"
  type: "Pooling"
  bottom: "conv1"
  top: "pool1"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "conv2"
  type: "Convolution"
  bottom: "pool1"
  top: "conv2"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  convolution_param {
    num_output: 50
    kernel_size: 5
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "pool2"
  type: "Pooling"
  bottom: "conv2"
  top: "pool2"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "ip1"
  type: "InnerProduct"
  bottom: "pool2"
  top: "ip1"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  inner_product_param {
    num_output: 500
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "relu1"
  type: "ReLU"
  bottom: "ip1"
  top: "ip1"
}
layer {
  name: "ip2"
  type: "InnerProduct"
  bottom: "ip1"
  top: "ip2"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  inner_product_param {
    num_output: 10
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "prob"
  type: "Softmax"
  bottom: "ip2"
  top: "prob"
}

原文地址：https://www.cnblogs.com/cheungxiongwei/p/8732957.html