目标检测中的priorbox（anchor,default box）可视化（c++）

网络结构，是Yushiqi老师开源的人脸检测网络

四个用于检测的特征层信息如下：

层	尺寸	min_size(1:1)	priorboxes
conv3_3	40x40	10,16,24	40x40x3=4800
conv4_3	20x20	32,48	20x20x2=800
conv5_3	10x10	64,96	10x10x2=200
conv6_3	5x5	128,192,256	5x5x3=75

下面是可视化的代码：

//可视化默认框
cv::Mat Classifier::visualize_priorbox(const cv::Mat& img,vector<string> layer_names)
{
	Blob<float>* input_layer = net_->input_blobs()[0];
	input_layer->Reshape(1, num_channels_, input_geometry_.height, input_geometry_.width);

	net_->Reshape();

	std::vector<cv::Mat> input_channels;
	WrapInputLayer(&input_channels);

	Preprocess(img, &input_channels);

	net_->Forward();
	cv::Mat new_img;
	cv::resize(img, new_img, cv::Size(320, 320));

	for (int i = 0; i < layer_names.size(); i++)
	{
		string layer_name = layer_names[i];
		assert(net_->has_blob(layer_name));
		cout << "提取的prior层名：" << layer_name << endl;
		boost::shared_ptr<Blob<float> >  priorBlob = net_->blob_by_name(layer_name);
		std::cout << "形状信息为：" << priorBlob->shape_string() << std::endl;

		string conv_layer = layer_name.substr(0, 12);//截取前半部分，找到对应的normalize层
		cout << conv_layer << endl;
		assert(net_->has_blob(conv_layer));
		cout << "提取的conv层名：" << conv_layer << endl;
		boost::shared_ptr<Blob<float> >  convBlob = net_->blob_by_name(conv_layer);
		std::cout << "形状信息为：" << convBlob->shape_string() << std::endl;

		int num_priors_ = (priorBlob->height() / 4);//某个priorbox层的所有priorbox的个数（每个框占4个位置）
		int conv_w = convBlob->width();
		int conv_h = convBlob->height();
		
		int num_priors_grid = (priorBlob->height() / 4)/(conv_w*conv_h);//每个格子点上对应的priorbox的个数
		//int num_prior_grid = (conv1Blob->height() / 4);
		int channel = priorBlob->shape(1);
		int batch = priorBlob->shape(0);
		cout << "priorbox nums:" << num_priors_ << endl;
		const float* tmpValue = priorBlob->cpu_data();

		vector<NormalizedBBox> prior_bboxes;
		vector<vector<float> > prior_variances;
		GetPriorBBoxes(tmpValue, num_priors_, &prior_bboxes, &prior_variances);

		int start = num_priors_ /2 + (convBlob->width())*num_priors_grid/2;//选择图像最中间的那个点
		
		cout << "start from " << start <<" priorbox"<< endl;
		for (int i = start; i < start+num_priors_grid; i++)
		//for (int i = 0; i < num_priors_; i++)
		{
			NormalizedBBox bbox = prior_bboxes[i];
			int xmin = bbox.xmin() * 320;
			int ymin = bbox.ymin() * 320;
			int xmax = bbox.xmax() * 320;
			int ymax = bbox.ymax() * 320;

			int box_w = xmax - xmin;

			cv::Rect rect(xmin, ymin, xmax, ymax);//左上坐标（x,y）和矩形的长(x)宽(y)
			cv::Point pt1, pt2;
			pt1.x = xmin;
			pt1.y = ymin;
			pt2.x = xmax;
			pt2.y = ymax;
			cout << xmin << " " << ymin << " " << xmax << " " << ymax << endl;
			int b = rand() % 255 + 1;
			int g = rand() % 255 + 1;
			int r = rand() % 255 + 1;

			cv::rectangle(new_img, pt1, pt2, cvScalar(b, g, r), 1, 8, 0);
            //cv::putText(new_img, to_string(box_w), pt1, cv::FONT_HERSHEY_SIMPLEX, 0.3, cv::Scalar(b, g, r));
		}
	}
	
	return new_img;
}

主函数调用：

int main(int argc, char** argv) {
	if (argc != 6) {
		std::cerr << "Usage: " << argv[0]
			<< " deploy.prototxt network.caffemodel"
			<< " mean.binaryproto testimg" << std::endl;
		return 1;
	}

	//::google::InitGoogleLogging(argv[0]);

	string model_file = argv[1];//网络结构文件
	string trained_file = argv[2];//模型 
	string mean_file = argv[3];//均值文件，空着，使用均值
	Classifier classifier(model_file, trained_file, mean_file, 104, 117, 123);

	string layer_str = argv[4];//要可视化的层，可以同时写多个用逗号隔开
	string file = argv[5];//测试图片


	stringstream ss(layer_str);
	vector<string> layers;
	string item;
	while (getline(ss, item, ',')) {
		string ly = item.c_str();
		layers.push_back(ly);
	}


	cv::Mat img = cv::imread(file, -1);
	CHECK(!img.empty()) << "Unable to decode image " << file;


	cv::Mat priorboxes=classifier.visualize_priorbox(img,layers);
	imshow("priorboxs", priorboxes);
	cv::waitKey(0);

}

opencv输出的用于检测的4层对应的priorbox（注意，priorbox是相对于原图来说的，不是feature map ）

从左到右分别是conv3_3，conv4_3，conv5_3，conv6_3

这里的各个priorbox因为都用的是1:1的比例，所以重叠在一起，看起来是图中这种小格子，其实比这更大，下面是我修改的增加了2:1比例的priorbox图片

从左到右分别是conv3_3，conv4_3，conv5_3，conv6_3

 

如果要再清晰的话，可以只显示其中一个点处的1:1的priorboxes(这里只显示了前三层的，因为显示的时候实在是不好对齐)