feat: 切换后端至PaddleOCR-NCNN，切换工程为CMake
1.项目后端整体迁移至PaddleOCR-NCNN算法，已通过基本的兼容性测试 2.工程改为使用CMake组织，后续为了更好地兼容第三方库，不再提供QMake工程 3.重整权利声明文件，重整代码工程，确保最小化侵权风险 Log: 切换后端至PaddleOCR-NCNN，切换工程为CMake Change-Id: I4d5d2c5d37505a4a24b389b1a4c5d12f17bfa38c
This commit is contained in:
wangzhengyang
170
3rdparty/opencv-4.5.4/samples/dnn/classification.cpp
vendored
Normal file
170
3rdparty/opencv-4.5.4/samples/dnn/classification.cpp
vendored
Normal file
@ -0,0 +1,170 @@
|
||||
#include <fstream>
|
||||
#include <sstream>
|
||||
|
||||
#include <opencv2/dnn.hpp>
|
||||
#include <opencv2/imgproc.hpp>
|
||||
#include <opencv2/highgui.hpp>
|
||||
|
||||
#include "common.hpp"
|
||||
|
||||
std::string keys =
|
||||
"{ help h | | Print help message. }"
|
||||
"{ @alias | | An alias name of model to extract preprocessing parameters from models.yml file. }"
|
||||
"{ zoo | models.yml | An optional path to file with preprocessing parameters }"
|
||||
"{ input i | | Path to input image or video file. Skip this argument to capture frames from a camera.}"
|
||||
"{ initial_width | 0 | Preprocess input image by initial resizing to a specific width.}"
|
||||
"{ initial_height | 0 | Preprocess input image by initial resizing to a specific height.}"
|
||||
"{ std | 0.0 0.0 0.0 | Preprocess input image by dividing on a standard deviation.}"
|
||||
"{ crop | false | Preprocess input image by center cropping.}"
|
||||
"{ framework f | | Optional name of an origin framework of the model. Detect it automatically if it does not set. }"
|
||||
"{ classes | | Optional path to a text file with names of classes. }"
|
||||
"{ backend | 0 | Choose one of computation backends: "
|
||||
"0: automatically (by default), "
|
||||
"1: Halide language (http://halide-lang.org/), "
|
||||
"2: Intel's Deep Learning Inference Engine (https://software.intel.com/openvino-toolkit), "
|
||||
"3: OpenCV implementation, "
|
||||
"4: VKCOM, "
|
||||
"5: CUDA },"
|
||||
"{ target | 0 | Choose one of target computation devices: "
|
||||
"0: CPU target (by default), "
|
||||
"1: OpenCL, "
|
||||
"2: OpenCL fp16 (half-float precision), "
|
||||
"3: VPU, "
|
||||
"4: Vulkan, "
|
||||
"6: CUDA, "
|
||||
"7: CUDA fp16 (half-float preprocess) }";
|
||||
|
||||
using namespace cv;
|
||||
using namespace dnn;
|
||||
|
||||
std::vector<std::string> classes;
|
||||
|
||||
int main(int argc, char** argv)
|
||||
{
|
||||
CommandLineParser parser(argc, argv, keys);
|
||||
|
||||
const std::string modelName = parser.get<String>("@alias");
|
||||
const std::string zooFile = parser.get<String>("zoo");
|
||||
|
||||
keys += genPreprocArguments(modelName, zooFile);
|
||||
|
||||
parser = CommandLineParser(argc, argv, keys);
|
||||
parser.about("Use this script to run classification deep learning networks using OpenCV.");
|
||||
if (argc == 1 || parser.has("help"))
|
||||
{
|
||||
parser.printMessage();
|
||||
return 0;
|
||||
}
|
||||
|
||||
int rszWidth = parser.get<int>("initial_width");
|
||||
int rszHeight = parser.get<int>("initial_height");
|
||||
float scale = parser.get<float>("scale");
|
||||
Scalar mean = parser.get<Scalar>("mean");
|
||||
Scalar std = parser.get<Scalar>("std");
|
||||
bool swapRB = parser.get<bool>("rgb");
|
||||
bool crop = parser.get<bool>("crop");
|
||||
int inpWidth = parser.get<int>("width");
|
||||
int inpHeight = parser.get<int>("height");
|
||||
String model = findFile(parser.get<String>("model"));
|
||||
String config = findFile(parser.get<String>("config"));
|
||||
String framework = parser.get<String>("framework");
|
||||
int backendId = parser.get<int>("backend");
|
||||
int targetId = parser.get<int>("target");
|
||||
|
||||
// Open file with classes names.
|
||||
if (parser.has("classes"))
|
||||
{
|
||||
std::string file = parser.get<String>("classes");
|
||||
std::ifstream ifs(file.c_str());
|
||||
if (!ifs.is_open())
|
||||
CV_Error(Error::StsError, "File " + file + " not found");
|
||||
std::string line;
|
||||
while (std::getline(ifs, line))
|
||||
{
|
||||
classes.push_back(line);
|
||||
}
|
||||
}
|
||||
|
||||
if (!parser.check())
|
||||
{
|
||||
parser.printErrors();
|
||||
return 1;
|
||||
}
|
||||
CV_Assert(!model.empty());
|
||||
|
||||
//! [Read and initialize network]
|
||||
Net net = readNet(model, config, framework);
|
||||
net.setPreferableBackend(backendId);
|
||||
net.setPreferableTarget(targetId);
|
||||
//! [Read and initialize network]
|
||||
|
||||
// Create a window
|
||||
static const std::string kWinName = "Deep learning image classification in OpenCV";
|
||||
namedWindow(kWinName, WINDOW_NORMAL);
|
||||
|
||||
//! [Open a video file or an image file or a camera stream]
|
||||
VideoCapture cap;
|
||||
if (parser.has("input"))
|
||||
cap.open(parser.get<String>("input"));
|
||||
else
|
||||
cap.open(0);
|
||||
//! [Open a video file or an image file or a camera stream]
|
||||
|
||||
// Process frames.
|
||||
Mat frame, blob;
|
||||
while (waitKey(1) < 0)
|
||||
{
|
||||
cap >> frame;
|
||||
if (frame.empty())
|
||||
{
|
||||
waitKey();
|
||||
break;
|
||||
}
|
||||
|
||||
if (rszWidth != 0 && rszHeight != 0)
|
||||
{
|
||||
resize(frame, frame, Size(rszWidth, rszHeight));
|
||||
}
|
||||
|
||||
//! [Create a 4D blob from a frame]
|
||||
blobFromImage(frame, blob, scale, Size(inpWidth, inpHeight), mean, swapRB, crop);
|
||||
|
||||
// Check std values.
|
||||
if (std.val[0] != 0.0 && std.val[1] != 0.0 && std.val[2] != 0.0)
|
||||
{
|
||||
// Divide blob by std.
|
||||
divide(blob, std, blob);
|
||||
}
|
||||
//! [Create a 4D blob from a frame]
|
||||
|
||||
//! [Set input blob]
|
||||
net.setInput(blob);
|
||||
//! [Set input blob]
|
||||
//! [Make forward pass]
|
||||
Mat prob = net.forward();
|
||||
//! [Make forward pass]
|
||||
|
||||
//! [Get a class with a highest score]
|
||||
Point classIdPoint;
|
||||
double confidence;
|
||||
minMaxLoc(prob.reshape(1, 1), 0, &confidence, 0, &classIdPoint);
|
||||
int classId = classIdPoint.x;
|
||||
//! [Get a class with a highest score]
|
||||
|
||||
// Put efficiency information.
|
||||
std::vector<double> layersTimes;
|
||||
double freq = getTickFrequency() / 1000;
|
||||
double t = net.getPerfProfile(layersTimes) / freq;
|
||||
std::string label = format("Inference time: %.2f ms", t);
|
||||
putText(frame, label, Point(0, 15), FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0, 255, 0));
|
||||
|
||||
// Print predicted class.
|
||||
label = format("%s: %.4f", (classes.empty() ? format("Class #%d", classId).c_str() :
|
||||
classes[classId].c_str()),
|
||||
confidence);
|
||||
putText(frame, label, Point(0, 40), FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0, 255, 0));
|
||||
|
||||
imshow(kWinName, frame);
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
Reference in New Issue
Block a user