1.编译ssd-caffe，在.build/examples/ssd/下生成ssd_detect.bin
查看ssd_detect.cpp参数，输入测试网络，测试模型，图片/视频列表，文件类型（图像/视频），阈值。输出带有检测坐标信息的文本。
// This is a demo code for using a SSD model to do detection.
// The code is modified from examples/cpp_classification/classification.cpp.
// Usage:
// ssd_detect [FLAGS] model_file weights_file list_file
//
// where model_file is the .prototxt file defining the network architecture, and
// weights_file is the .caffemodel file containing the network parameters, and
// list_file contains a list of image files with the format as follows:
// folder/img1.JPEG
// folder/img2.JPEG
// list_file can also contain a list of video files with the format as follows:
// folder/video1.mp4
// folder/video2.mp4
//
#include <caffe/caffe.hpp>
#ifdef USE_OPENCV
#include <opencv2/core/core.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#endif // USE_OPENCV
#include <algorithm>
#include <iomanip>
#include <iosfwd>
#include <memory>
#include <string>
#include <utility>
#include <vector>
#ifdef USE_OPENCV
using namespace caffe; // NOLINT(build/namespaces)
class Detector {
public:
Detector(const string& model_file,
const string& weights_file,
const string& mean_file,
const string& mean_value);
std::vector<vector<float> > Detect(const cv::Mat& img);
private:
void SetMean(const string& mean_file, const string& mean_value);
void WrapInputLayer(std::vector<cv::Mat>* input_channels);
void Preprocess(const cv::Mat& img,
std::vector<cv::Mat>* input_channels);
private:
shared_ptr<Net<float> > net_;
cv::Size input_geometry_;
int num_channels_;
cv::Mat mean_;
};
Detector::Detector(const string& model_file,
const string& weights_file,
const string& mean_file,
const string& mean_value) {
#ifdef CPU_ONLY
Caffe::set_mode(Caffe::CPU);
#else
Caffe::set_mode(Caffe::GPU);
#endif
/* Load the network. */
net_.reset(new Net<float>(model_file, TEST));
net_->CopyTrainedLayersFrom(weights_file);
CHECK_EQ(net_->num_inputs(), 1) << "Network should have exactly one input.";
CHECK_EQ(net_->num_outputs(), 1) << "Network should have exactly one output.";
Blob<float>* input_layer = net_->input_blobs()[0];
num_channels_ = input_layer->channels();
CHECK(num_channels_ == 3 || num_channels_ == 1)
<< "Input layer should have 1 or 3 channels.";
input_geometry_ = cv::Size(input_layer->width(), input_layer->height());
/* Load the binaryproto mean file. */
SetMean(mean_file, mean_value);
}
std::vector<vector<float> > Detector::Detect(const cv::Mat& img) {
Blob<float>* input_layer = net_->input_blobs()[0];
input_layer->Reshape(1, num_channels_,
input_geometry_.height, input_geometry_.width);
/* Forward dimension change to all layers. */
net_->Reshape();
std::vector<cv::Mat> input_channels;
WrapInputLayer(&input_channels);
Preprocess(img, &input_channels);
net_->Forward();
/* Copy the output layer to a std::vector */
Blob<float>* result_blob = net_->output_blobs()[0];
const float* result = result_blob->cpu_data();
const int num_det = result_blob->height();
vector<vector<float> > detections;
for (int k = 0; k < num_det; ++k) {
if (result[0] == -1) {
// Skip invalid detection.
result += 7;
continue;
}
vector<float> detection(result, result + 7);
detections.push_back(detection);
result += 7;
}
return detections;
}
/* Load the mean file in binaryproto format. */
void Detector::SetMean(const string& mean_file, const string& mean_value) {
cv::Scalar channel_mean;
if (!mean_file.empty()) {
CHECK(mean_value.empty()) <<
"Cannot specify mean_file and mean_value at the same time";
BlobProto blob_proto;
ReadProtoFromBinaryFileOrDie(mean_file.c_str(), &blob_proto);
/* Convert from BlobProto to Blob<float> */
Blob<float> mean_blob;
mean_blob.FromProto(blob_proto);
CHECK_EQ(mean_blob.channels(), num_channels_)
<< "Number of channels of mean file doesn't match input layer.";
/* The format of the mean file is planar 32-bit float BGR or grayscale. */
std::vector<cv::Mat> channels;
float* data = mean_blob.mutable_cpu_data();
for (int i = 0; i < num_channels_; ++i) {
/* Extract an individual channel. */
cv::Mat channel(mean_blob.height(), mean_blob.width(), CV_32FC1, data);
channels.push_back(channel);
data += mean_blob.height() * mean_blob.width();
}
/* Merge the separate channels into a single image. */
cv::Mat mean;
cv::merge(channels, mean);
/* Compute the global mean pixel value and create a mean image
* filled with this value. */
channel_mean = cv::mean(mean);
mean_ = cv::Mat(input_geometry_, mean.type(), channel_mean);
}
if (!mean_value.empty()) {
CHECK(mean_file.empty()) <<
"Cannot specify mean_file and mean_value at the same time";
stringstream ss(mean_value);
vector<float> values;
string item;
while (getline(ss, item, ',')) {
float value = std::atof(item.c_str());
values.push_back(value);
}
CHECK(values.size() == 1 || values.size() == num_channels_) <<
"Specify either 1 mean_value or as many as channels: " << num_channels_;
std::vector<cv::Mat> channels;
for (int i = 0; i < num_channels_; ++i) {
/* Extract an individual channel. */
cv::Mat channel(input_geometry_.height, input_geometry_.width, CV_32FC1,
cv::Scalar(values[i]));
channels.push_back(channel);
}
cv::merge(channels, mean_);
}
}
/* Wrap the input layer of the network in separate cv::Mat objects
* (one per channel). This way we save one memcpy operation and we
* don't need to rely on cudaMemcpy2D. The last preprocessing
* operation will write the separate channels directly to the input
* layer. */
void Detector::WrapInputLayer(std::vector<cv::Mat>* input_channels) {
Blob<float>* input_layer = net_->input_blobs()[0];
int width = input_layer->width();
int height = input_layer->height();
float* input_data = input_layer->mutable_cpu_data();
for (int i = 0; i < input_layer->channels(); ++i) {
cv::Mat channel(height, width, CV_32FC1, input_data);
input_channels->push_back(channel);
input_data += width * height;
}
}
void Detector::Preprocess(const cv::Mat& img,
std::vector<cv::Mat>* input_channels) {
/* Convert the input image to the input image format of the network. */
cv::Mat sample;
if (img.channels() == 3 && num_channels_ == 1)
cv::cvtColor(img, sample, cv::COLOR_BGR2GRAY);
else if (img.channels() == 4 && num_channels_ == 1)
cv::cvtColor(img, sample, cv::COLOR_BGRA2GRAY);
else if (img.channels() == 4 && num_channels_ == 3)
cv::cvtColor(img, sample, cv::COLOR_BGRA2BGR);
else if (img.channels() == 1 && num_channels_ == 3)
cv::cvtColor(img, sample, cv::COLOR_GRAY2BGR);
else
sample = img;
cv::Mat sample_resized;
if (sample.size() != input_geometry_)
cv::resize(sample, sample_resized, input_geometry_);
else
sample_resized = sample;
cv::Mat sample_float;
if (num_channels_ == 3)
sample_resized.convertTo(sample_float, CV_32FC3);
else
sample_resized.convertTo(sample_float, CV_32FC1);
cv::Mat sample_normalized;
cv::subtract(sample_float, mean_, sample_normalized);
/* This operation will write the separate BGR planes directly to the
* input layer of the network because it is wrapped by the cv::Mat
* objects in input_channels. */
cv::split(sample_normalized, *input_channels);
CHECK(reinterpret_cast<float*>(input_channels->at(0).data)
== net_->input_blobs()[0]->cpu_data())
<< "Input channels are not wrapping the input layer of the network.";
}
DEFINE_string(mean_file, "",
"The mean file used to subtract from the input image.");
DEFINE_string(mean_value, "104,117,123",
"If specified, can be one value or can be same as image channels"
" - would subtract from the corresponding channel). Separated by ','."
"Either mean_file or mean_value should be provided, not both.");
DEFINE_string(file_type, "image",
"The file type in the list_file. Currently support image and video.");
DEFINE_string(out_file, "",
"If provided, store the detection results in the out_file.");
DEFINE_double(confidence_threshold, 0.01,
"Only store detections with score higher than the threshold.");
int main(int argc, char** argv) {
::google::InitGoogleLogging(argv[0]);
// Print output to stderr (while still logging)
FLAGS_alsologtostderr = 1;
#ifndef GFLAGS_GFLAGS_H_
namespace gflags = google;
#endif
gflags::SetUsageMessage("Do detection using SSD mode.\n"
"Usage:\n"
" ssd_detect [FLAGS] model_file weights_file list_file\n");
gflags::ParseCommandLineFlags(&argc, &argv, true);
if (argc < 4) {
gflags::ShowUsageWithFlagsRestrict(argv[0], "examples/ssd/ssd_detect");
return 1;
}
const string& model_file = argv[1];
const string& weights_file = argv[2];
const string& mean_file = FLAGS_mean_file;
const string& mean_value = FLAGS_mean_value;
const string& file_type = FLAGS_file_type;
const string& out_file = FLAGS_out_file;
const float confidence_threshold = FLAGS_confidence_threshold;
// Initialize the network.
Detector detector(model_file, weights_file, mean_file, mean_value);
// Set the output mode.
std::streambuf* buf = std::cout.rdbuf();
std::ofstream outfile;
if (!out_file.empty()) {
outfile.open(out_file.c_str());
if (outfile.good()) {
buf = outfile.rdbuf();
}
}
std::ostream out(buf);
// Process image one by one.
std::ifstream infile(argv[3]);
std::string file;
while (infile >> file) {
if (file_type == "image") {
cv::Mat img = cv::imread(file, -1);
CHECK(!img.empty()) << "Unable to decode image " << file;
std::vector<vector<float> > detections = detector.Detect(img);
/* Print the detection results. */
for (int i = 0; i < detections.size(); ++i) {
const vector<float>& d = detections[i];
// Detection format: [image_id, label, score, xmin, ymin, xmax, ymax].
CHECK_EQ(d.size(), 7);
const float score = d[2];
if (score >= confidence_threshold) {
out << file << " ";
out << static_cast<int>(d[1]) << " ";
out << score << " ";
out << static_cast<int>(d[3] * img.cols) << " ";
out << static_cast<int>(d[4] * img.rows) << " ";
out << static_cast<int>(d[5] * img.cols) << " ";
out << static_cast<int>(d[6] * img.rows) << std::endl;
}
}
} else if (file_type == "video") {
cv::VideoCapture cap(file);
if (!cap.isOpened()) {
LOG(FATAL) << "Failed to open video: " << file;
}
cv::Mat img;
int frame_count = 0;
while (true) {
bool success = cap.read(img);
if (!success) {
LOG(INFO) << "Process " << frame_count << " frames from " << file;
break;
}
CHECK(!img.empty()) << "Error when read frame";
std::vector<vector<float> > detections = detector.Detect(img);
/* Print the detection results. */
for (int i = 0; i < detections.size(); ++i) {
const vector<float>& d = detections[i];
// Detection format: [image_id, label, score, xmin, ymin, xmax, ymax].
CHECK_EQ(d.size(), 7);
const float score = d[2];
if (score >= confidence_threshold) {
out << file << "_";
out << std::setfill('0') << std::setw(6) << frame_count << " ";
out << static_cast<int>(d[1]) << " ";
out << score << " ";
out << static_cast<int>(d[3] * img.cols) << " ";
out << static_cast<int>(d[4] * img.rows) << " ";
out << static_cast<int>(d[5] * img.cols) << " ";
out << static_cast<int>(d[6] * img.rows) << std::endl;
}
}
++frame_count;
}
if (cap.isOpened()) {
cap.release();
}
} else {
LOG(FATAL) << "Unknown file_type: " << file_type;
}
}
return 0;
}
#else
int main(int argc, char** argv) {
LOG(FATAL) << "This example requires OpenCV; compile with USE_OPENCV.";
}
#endif // USE_OPENCV
2.批处理脚本
ssd_detect_pic.sh
#!/usr/bin/env sh ./build/examples/ssd/ssd_detect.bin \ models/VGGNet/SSD_300x300/deploy.prototxt \ models/VGGNet/SSD_300x300/SSD_300x300_iter_30000.caffemodel \ examples/images/name.txt \ --file_type image \ --out_file output.txt \ --confidence_threshold 0.45 echo "Done."
name.txt中的待处理图像列表为caffe根目录下的相对路径
ssd_detect_video.sh
#!/usr/bin/env sh ./build/examples/ssd/ssd_detect.bin \ models/VGGNet/SSD_300x300/deploy.prototxt \ models/VGGNet/SSD_300x300/SSD_300x300_iter_80000.caffemodel \ examples/videos/test.txt \ --file_type video \ --out_file output.txt \ --confidence_threshold 0.4 echo "Done."
3.自动标注
https://blog.csdn.net/sinat_30071459/article/details/50723212
该作者提供了一种手动画框标注图像的方法，得到对应图像的目标信息框并保存到txt，再用matlab将txt中的坐标对应生成到xml文件，其中框到的目标位置信息格式如下：
jpg 数字label x1 y1 x2 y2
而之前使用ssd_detect得到的输出文件中格式：
jpg 标签label confidence x1 y1 x2 y2
对比仅仅多了confidence列，因此很容易想到流程，将一批待标记的图，用现有的检测模型先获得txt位置坐标信息，去除confidence列，替换数字label为标签label，再用matlab生成xml文件。流程有点多，但是至少比直接在原图上标记来的方便。注：自动标注需要一个已经训练好的模型。
删除第三列
awk '{$3="";print $0}' output.txt > new_output.txt
待处理图像和转换后的txt文件放在img文件夹，执行VOC2007xml.m，Annotations生成xml文件，JPEGImages下对应jpg文件，最后JPEGImages文件数量<=img文件数量，原因是模型可能会比较差，部分图不一定检测到结果。
VOC2007xml.m
%%
%自动标注
%用ssd_detect先处理待标记图像得到txt
%转换txt
%txt文件每行格式为：000002.jpg dog 44 28 132 121
%即每行由图片名、目标类型、包围框坐标组成，空格隔开
%如果一张图片有多个目标，则格式如下：（比如两个目标）
%000002.jpg dog 44 28 132 121
%000002.jpg car 50 27 140 110
%包围框坐标为左上角和右下角
%原作者小咸鱼_CSDN:http://blog.csdn.net/sinat_30071459
%matlab程序增加溢出保护，有转换偏差可能出现坐标为-1，-2，或者图像宽高+1，+2的情况，这部分加入训练集会报错。
%详细见：https://blog.csdn.net/cgt19910923
%%
clc;
clear;
%注意修改下面四个变量
imgpath='img\';%图像存放文件夹
txtpath='img\new_output.txt';%txt文件
xmlpath_new='Annotations/';%修改后的xml保存文件夹
foldername='VOC2007';%xml的folder字段名
fidin=fopen(txtpath,'r');
lastname='begin';
while ~feof(fidin)
tline=fgetl(fidin);
str = regexp(tline, ' ','split');
filepath=[imgpath,str{1}];
img=imread(filepath);
[h,w,d]=size(img);
imshow(img);
rectangle('Position',[str2double(str{3}),str2double(str{4}),str2double(str{5})-str2double(str{3}),str2double(str{6})-str2double(str{4})],'LineWidth',4,'EdgeColor','r');
pause(0.1);
if strcmp(str{1},lastname)%如果文件名相等，只需增加object
object_node=Createnode.createElement('object');
Root.appendChild(object_node);
node=Createnode.createElement('name');
node.appendChild(Createnode.createTextNode(sprintf('%s',str{2})));
object_node.appendChild(node);
node=Createnode.createElement('pose');
node.appendChild(Createnode.createTextNode(sprintf('%s','Unspecified')));
object_node.appendChild(node);
node=Createnode.createElement('truncated');
node.appendChild(Createnode.createTextNode(sprintf('%s','0')));
object_node.appendChild(node);
node=Createnode.createElement('difficult');
node.appendChild(Createnode.createTextNode(sprintf('%s','0')));
object_node.appendChild(node);
bndbox_node=Createnode.createElement('bndbox');
object_node.appendChild(bndbox_node);
node=Createnode.createElement('xmin');
if str2double(str{3})<0
node.appendChild(Createnode.createTextNode(sprintf('%s','0')));
bndbox_node.appendChild(node);
else
node.appendChild(Createnode.createTextNode(sprintf('%s',num2str(str{3}))));
bndbox_node.appendChild(node);
end
node=Createnode.createElement('ymin');
if str2double(str{4})<0
node.appendChild(Createnode.createTextNode(sprintf('%s','0')));
bndbox_node.appendChild(node);
else
node.appendChild(Createnode.createTextNode(sprintf('%s',num2str(str{4}))));
bndbox_node.appendChild(node);
end
node=Createnode.createElement('xmax');
if str2double(str{5})>w
node.appendChild(Createnode.createTextNode(sprintf('%s',num2str(w))));
bndbox_node.appendChild(node);
else
node.appendChild(Createnode.createTextNode(sprintf('%s',num2str(str{5}))));
bndbox_node.appendChild(node);
end
node=Createnode.createElement('ymax');
if str2double(str{6})>h
node.appendChild(Createnode.createTextNode(sprintf('%s',num2str(h))));
bndbox_node.appendChild(node);
else
node.appendChild(Createnode.createTextNode(sprintf('%s',num2str(str{6}))));
bndbox_node.appendChild(node);
end
else %如果文件名不等，则需要新建xml
copyfile(filepath, 'JPEGImages');
%先保存上一次的xml
if exist('Createnode','var')
tempname=lastname;
tempname=strrep(tempname,'.jpg','.xml');
xmlwrite(tempname,Createnode);
end
Createnode=com.mathworks.xml.XMLUtils.createDocument('annotation');
Root=Createnode.getDocumentElement;%根节点
node=Createnode.createElement('folder');
node.appendChild(Createnode.createTextNode(sprintf('%s',foldername)));
Root.appendChild(node);
node=Createnode.createElement('filename');
node.appendChild(Createnode.createTextNode(sprintf('%s',str{1})));
Root.appendChild(node);
source_node=Createnode.createElement('source');
Root.appendChild(source_node);
node=Createnode.createElement('database');
node.appendChild(Createnode.createTextNode(sprintf('My Database')));
source_node.appendChild(node);
node=Createnode.createElement('annotation');
node.appendChild(Createnode.createTextNode(sprintf('VOC2007')));
source_node.appendChild(node);
node=Createnode.createElement('image');
node.appendChild(Createnode.createTextNode(sprintf('flickr')));
source_node.appendChild(node);
node=Createnode.createElement('flickrid');
node.appendChild(Createnode.createTextNode(sprintf('NULL')));
source_node.appendChild(node);
owner_node=Createnode.createElement('owner');
Root.appendChild(owner_node);
node=Createnode.createElement('flickrid');
node.appendChild(Createnode.createTextNode(sprintf('NULL')));
owner_node.appendChild(node);
node=Createnode.createElement('name');
node.appendChild(Createnode.createTextNode(sprintf('xiaoxianyu')));
owner_node.appendChild(node);
size_node=Createnode.createElement('size');
Root.appendChild(size_node);
node=Createnode.createElement('width');
node.appendChild(Createnode.createTextNode(sprintf('%s',num2str(w))));
size_node.appendChild(node);
node=Createnode.createElement('height');
node.appendChild(Createnode.createTextNode(sprintf('%s',num2str(h))));
size_node.appendChild(node);
node=Createnode.createElement('depth');
node.appendChild(Createnode.createTextNode(sprintf('%s',num2str(d))));
size_node.appendChild(node);
node=Createnode.createElement('segmented');
node.appendChild(Createnode.createTextNode(sprintf('%s','0')));
Root.appendChild(node);
object_node=Createnode.createElement('object');
Root.appendChild(object_node);
node=Createnode.createElement('name');
node.appendChild(Createnode.createTextNode(sprintf('%s',str{2})));
object_node.appendChild(node);
node=Createnode.createElement('pose');
node.appendChild(Createnode.createTextNode(sprintf('%s','Unspecified')));
object_node.appendChild(node);
node=Createnode.createElement('truncated');
node.appendChild(Createnode.createTextNode(sprintf('%s','0')));
object_node.appendChild(node);
node=Createnode.createElement('difficult');
node.appendChild(Createnode.createTextNode(sprintf('%s','0')));
object_node.appendChild(node);
bndbox_node=Createnode.createElement('bndbox');
object_node.appendChild(bndbox_node);
node=Createnode.createElement('xmin');
if str2double(str{3})<0
node.appendChild(Createnode.createTextNode(sprintf('%s','0')));
bndbox_node.appendChild(node);
else
node.appendChild(Createnode.createTextNode(sprintf('%s',num2str(str{3}))));
bndbox_node.appendChild(node);
end
node=Createnode.createElement('ymin');
if str2double(str{4})<0
node.appendChild(Createnode.createTextNode(sprintf('%s','0')));
bndbox_node.appendChild(node);
else
node.appendChild(Createnode.createTextNode(sprintf('%s',num2str(str{4}))));
bndbox_node.appendChild(node);
end
node=Createnode.createElement('xmax');
if str2double(str{5})>w
node.appendChild(Createnode.createTextNode(sprintf('%s',num2str(w))));
bndbox_node.appendChild(node);
else
node.appendChild(Createnode.createTextNode(sprintf('%s',num2str(str{5}))));
bndbox_node.appendChild(node);
end
node=Createnode.createElement('ymax');
if str2double(str{6})>h
node.appendChild(Createnode.createTextNode(sprintf('%s',num2str(h))));
bndbox_node.appendChild(node);
else
node.appendChild(Createnode.createTextNode(sprintf('%s',num2str(str{6}))));
bndbox_node.appendChild(node);
end
lastname=str{1};
end
%处理最后一行
if feof(fidin)
tempname=lastname;
tempname=strrep(tempname,'.jpg','.xml');
xmlwrite(tempname,Createnode);
end
end
fclose(fidin);
file=dir(pwd);
for i=1:length(file)
if length(file(i).name)>=4 && strcmp(file(i).name(end-3:end),'.xml')
fold=fopen(file(i).name,'r');
fnew=fopen([xmlpath_new file(i).name],'w');
line=1;
while ~feof(fold)
tline=fgetl(fold);
if line==1
line=2;
continue;
end
expression = ' ';
replace=char(9);
newStr=regexprep(tline,expression,replace);
fprintf(fnew,'%s\n',newStr);
end
fprintf('已处理%s\n',file(i).name);
fclose(fold);
fclose(fnew);
delete(file(i).name);
end
end
标注程序下载：https://pan.baidu.com/s/1dWTjAPKi4HcVs-RW7JEATQ