Fork me on GitHub

OpenCv dnn模块扩展研究(1)--style transfer



代码流程均较简单:图像转Blob,forward,处理输出结果,显示。【可以说是OpenCV Dnn使用方面的经典入门,对于我们对流程配置、参数理解都有很好帮助】
// This script is used to run style transfer models from '
// using OpenCV
#include <opencv2/dnn.hpp>
#include <opencv2/imgproc.hpp>
#include <opencv2/highgui.hpp>
#include <iostream>
using namespace cv;
using namespace cv::dnn;
using namespace std;
int main(int argc, char **argv)
    string modelBin = "../../data/testdata/dnn/fast_neural_style_instance_norm_feathers.t7";
    string imageFile = "../../data/image/chicago.jpg";
    float scale = 1.0;
    cv::Scalar mean { 103.939, 116.779, 123.68 };
    bool swapRB = false;
    bool crop = false;
    bool useOpenCL = false;
    Mat img = imread(imageFile);
    if (img.empty()) {
        cout << "Can't read image from file: " << imageFile << endl;
        return 2;
    // Load model
    Net net = dnn::readNetFromTorch(modelBin);
    if (useOpenCL)
    // Create a 4D blob from a frame.
    Mat inputBlob = blobFromImage(img,scale, img.size(),mean,swapRB,crop);
    // forward netword
    Mat output = net.forward();
    // process output
    Mat(output.size[2], output.size[3], CV_32F, output.ptr<float>(0, 0)) += 103.939;
    Mat(output.size[2], output.size[3], CV_32F, output.ptr<float>(0, 1)) += 116.779;
    Mat(output.size[2], output.size[3], CV_32F, output.ptr<float>(0, 2)) += 123.68;
    std::vector<cv::Mat> ress;
    imagesFromBlob(output, ress);
    // show res
    Mat res;
    ress[0].convertTo(res, CV_8UC3);
    imshow("reslut", res);
    imshow("origin", img);
    return 0;




Training new models

To train new style transfer models, first use the scriptscripts/ to create an HDF5 file from folders of images.You will then use the script train.lua to actually train models.

Step 1: Prepare a dataset

You first need to install the header files for Python 2.7 and HDF5. On Ubuntuyou should be able to do the following:

sudo apt-get -y install python2.7-dev
sudo apt-get install libhdf5-dev

You can then install Python dependencies into a virtual environment:

virtualenv .env                  # Create the virtual environmentsource .env/bin/activate         # Activate the virtual environment
pip install -r requirements.txt 
# Install Python dependencies# Work for a while ...
# Exit the virtual environment

With the virtual environment activated, you can use the scriptscripts/ to create an HDF5 file from a directory oftraining images and a directory of validation images:

python scripts/ \
  --train_dir path/to/training/images \
  --val_dir path/to/validation/images \
  --output_file path/to/output/file.h5

All models in thisrepository were trained using the images from theCOCO dataset.

The preprocessing script has the following flags:

  • --train_dir: Path to a directory of training images.
  • --val_dir: Path to a directory of validation images.
  • --output_file: HDF5 file where output will be written.
  • --height, --width: All images will be resized to this size.
  • --max_images: The maximum number of images to use for trainingand validation; -1 means use all images in the directories.
  • --num_workers: The number of threads to use.

Step 2: Train a model

After creating an HDF5 dataset file, you can use the script train.lua totrain feedforward style transfer models. First you need to download aTorch version of theVGG-16 modelby running the script

bash models/

This will download the file vgg16.t7 (528 MB) to the models directory.

You will also need to installdeepmind/torch-hdf5which gives HDF5 bindings for Torch:

luarocks install

You can then train a model with the script train.lua. For basic usage thecommand will look something like this:

th train.lua \
  -h5_file path/to/dataset.h5 \
  -style_image path/to/style/image.jpg \
  -style_image_size 384 \
  -content_weights 1.0 \
  -style_weights 5.0 \
  -checkpoint_name checkpoint \
  -gpu 0

The full set of options for this script are described here.


posted @ 2019-05-03 07:51  jsxyhelu  阅读(...)  评论(...编辑  收藏