opencv dnn模块 示例(12) 图像风格化 style transfer

一、opencv的示例模型文件

使用Torch模型，下载地址：fast_neural_style_eccv16_starry_night.t7和fast_neural_style_instance_norm_feathers.t7。

二、示例代码

c++和py代码流程均较简单：图像转Blob，forward，处理输出结果，显示。

c++代码如下：

// This script is used to run style transfer models from '
// https://github.com/jcjohnson/fast-neural-style 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)
		net.setPreferableTarget(DNN_TARGET_OPENCL);
	
	// Create a 4D blob from a frame.
	Mat inputBlob = blobFromImage(img,scale, img.size(),mean,swapRB,crop);

	// forward netword
	net.setInput(inputBlob);
	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);

	waitKey();
	return 0;
}

python代码如下：

from __future__ import print_function
import cv2 as cv
import numpy as np
import argparse

parser = argparse.ArgumentParser(
        description='This script is used to run style transfer models from '
                    'https://github.com/jcjohnson/fast-neural-style using OpenCV')
parser.add_argument('--input', help='Path to image or video. Skip to capture frames from camera')
parser.add_argument('--model', help='Path to .t7 model')
parser.add_argument('--width', default=-1, type=int, help='Resize input to specific width.')
parser.add_argument('--height', default=-1, type=int, help='Resize input to specific height.')
parser.add_argument('--median_filter', default=0, type=int, help='Kernel size of postprocessing blurring.')
args = parser.parse_args()

args.model = "../data/testdata/dnn/fast_neural_style_instance_norm_feathers.t7"
args.input = "../data/image/chicago.jpg"


net = cv.dnn.readNetFromTorch(cv.samples.findFile(args.model))
net.setPreferableBackend(cv.dnn.DNN_BACKEND_OPENCV);

if args.input:
    cap = cv.VideoCapture(args.input)
else:
    cap = cv.VideoCapture(0)

cv.namedWindow('Styled image', cv.WINDOW_NORMAL)
while cv.waitKey(1) < 0:
    hasFrame, frame = cap.read()
    if not hasFrame:
        cv.waitKey()
        break

    inWidth = args.width if args.width != -1 else frame.shape[1]
    inHeight = args.height if args.height != -1 else frame.shape[0]
    inp = cv.dnn.blobFromImage(frame, 1.0, (inWidth, inHeight),
                              (103.939, 116.779, 123.68), swapRB=False, crop=False)

    net.setInput(inp)
    out = net.forward()

    out = out.reshape(3, out.shape[2], out.shape[3])
    out[0] += 103.939
    out[1] += 116.779
    out[2] += 123.68
    out /= 255
    out = out.transpose(1, 2, 0)

    t, _ = net.getPerfProfile()
    freq = cv.getTickFrequency() / 1000
    print(t / freq, 'ms')

    if args.median_filter:
        out = cv.medianBlur(out, args.median_filter)

    cv.imshow('Styled image', out)

三、演示

fast_neural_style_instance_norm_feathers.t7的演示效果


fast_neural_style_eccv16_starry_night.t7的演示效果：