优化代码

Code/TestTRTInterDll/TestTRTInterDll.cpp

@@ -0,0 +1,265 @@
+// TestTRTInterDll.cpp : 此文件包含 "main" 函数。程序执行将在此处开始并结束。
+//
+
+#include <iostream>
+#include <filesystem>
+#include <iostream>
+#include <string>
+#include "utils.h"
+#include "MI_Interface.h"
+#include <future>
+
+
+namespace fs = std::filesystem;
+
+bool buffer2Mat(const MN_VisionImage::MS_ImageParam& _inImg, cv::Mat& _mat);
+
+void test01()
+{
+	std::vector<std::string> imagePath;
+	imagePath.emplace_back("./imageDatas/daisy.jpg");
+	imagePath.emplace_back("./imageDatas/dandelion.jpg");
+	imagePath.emplace_back("./imageDatas/sunflower.jpg");
+	imagePath.emplace_back("./imageDatas/tulip.jpg");
+
+	std::vector<cv::Mat> matImgs;
+	for (auto _var : imagePath)
+	{
+		matImgs.emplace_back(cv::imread(_var, 1));
+	}
+
+	trtUtils::InitParameter params;
+	params.m_modelType = trtUtils::ME_ModelType::E_RESNET34;
+	params.class_names = trtUtils::dataSets::flower_labels;
+	//initParameters.class_names = utils::dataSets::voc20;
+	params.num_class = 5; // for flower_labels
+	//initParameters.num_class = 20; // for voc2012
+	params.batch_size = 1;
+	params.dst_h = 224;
+	params.dst_w = 224;
+	memcpy(&params.mImage.m_data, matImgs[0].data, sizeof(matImgs[0].rows * matImgs[0].cols * matImgs[0].channels()));
+	params.mImage.m_height = matImgs[0].rows;
+	params.mImage.m_width = matImgs[0].cols;
+	params.mImage.m_channels = 3;
+	params.input_output_names = { "input",  "output" };
+	params.conf_thresh = 0.25f;
+	params.iou_thresh = 0.45f;
+	params.save_path = "./imageDatas";
+	params.meanVec = { 0.406, 0.456, 0.485 };
+	params.stdVec = { 0.225, 0.224, 0.229 };
+	MI_VisionInterface* resnet34Ptr = getInterfacePtr(params);
+	if (!resnet34Ptr)
+	{
+		return;
+	}
+
+	trtUtils::InitParameter params1;
+	params1.m_modelType = trtUtils::ME_ModelType::E_RESNET50;
+	params1.class_names = trtUtils::dataSets::flower_labels;
+	//initParameters.class_names = utils::dataSets::voc20;
+	params1.num_class = 5; // for flower_labels
+	//initParameters.num_class = 20; // for voc2012
+	params1.batch_size = 1;
+	params1.dst_h = 224;
+	params1.dst_w = 224;
+	memcpy(&params1.mImage.m_data, matImgs[0].data, sizeof(matImgs[0].rows * matImgs[0].cols * matImgs[0].channels()));
+	params1.mImage.m_height = matImgs[0].rows;
+	params1.mImage.m_width = matImgs[0].cols;
+	params1.mImage.m_channels = 3;
+	params1.input_output_names = { "input",  "output" };
+	params1.conf_thresh = 0.25f;
+	params1.iou_thresh = 0.45f;
+	params1.save_path = "./imageDatas";
+	params1.meanVec = { 0.406, 0.456, 0.485 };
+	params1.stdVec = { 0.225, 0.224, 0.229 };
+	MI_VisionInterface* resnet50Ptr = getInterfacePtr(params1);
+	if (!resnet50Ptr)
+	{
+		return;
+	}
+
+	// 线程测试，初始化在一个线程，推理在另外一个线程内
+	std::string onnxFile = "./imageDatas/resnet34_0407.onnx";
+	std::string onnxFile1 = "./imageDatas/resnet50.onnx";
+
+#if 0
+	bool bRet = false;
+	bRet = resnetPtr->initEngine(onnxFile);
+	if (!bRet)
+	{
+		return;
+	}
+
+	bRet = resnetPtr->check();
+	if (!bRet)
+	{
+		return;
+	}
+
+	std::vector<MR_Result> detectResVec;
+	bRet = resnetPtr->doTRTInfer(matImgs, &detectResVec, nullptr);
+	if (!bRet)
+	{
+		return;
+	}
+#endif // 0
+
+	// 初始化线程
+	auto initRes = std::async(std::launch::async, [&] {
+
+		bool bRet = false;
+		// 加载第一个模型初始化并推理
+		bRet = resnet34Ptr->initEngine(onnxFile);
+		if (!bRet)
+		{
+			return false;
+		}
+
+		// 加载第二个模型初始化并推理
+		bRet = resnet50Ptr->initEngine(onnxFile1);
+		if (!bRet)
+		{
+			return false;
+		}
+
+		return true;
+		});
+	initRes.wait();
+
+	auto initRes1 = std::async(std::launch::async, [&] {
+
+		bool bRet = false;
+		bRet = resnet34Ptr->check();
+		if (!bRet)
+		{
+			return false;
+		}
+
+		std::vector<trtUtils::MR_Result> detectResVec1;
+		bRet = resnet34Ptr->doTRTInfer(matImgs, &detectResVec1, nullptr);
+		if (!bRet)
+		{
+			return false;
+		}
+
+		bRet = resnet50Ptr->check();
+		if (!bRet)
+		{
+			return false;
+		}
+
+		std::vector<trtUtils::MR_Result> detectResVec2;
+		bRet = resnet50Ptr->doTRTInfer(matImgs, &detectResVec2, nullptr);
+		if (!bRet)
+		{
+			return false;
+		}
+
+		return true;
+
+		});
+
+	//initRes1.wait();
+
+	auto initRes2 = std::async(std::launch::async, [&] {
+
+		bool bRet = false;
+		bRet = resnet34Ptr->check();
+		if (!bRet)
+		{
+			return false;
+		}
+
+		std::vector<trtUtils::MR_Result> detectResVec1;
+		bRet = resnet34Ptr->doTRTInfer(matImgs, &detectResVec1, nullptr);
+		if (!bRet)
+		{
+			return false;
+		}
+
+		bRet = resnet50Ptr->check();
+		if (!bRet)
+		{
+			return false;
+		}
+
+		std::vector<trtUtils::MR_Result> detectResVec2;
+		bRet = resnet50Ptr->doTRTInfer(matImgs, &detectResVec2, nullptr);
+		if (!bRet)
+		{
+			return false;
+		}
+
+		return true;
+		});
+
+	//initRes2.wait();
+
+}
+
+void test02()
+{
+	cv::Mat img = cv::imread("./imageDatas/daisy.jpg", 1);
+	MN_VisionImage::MS_ImageParam bufImg((uchar*)img.data, img.cols, img.rows, MN_VisionImage::ME_ImageType::E_RGB);
+
+	cv::Mat convertImg;
+	bool bRet = buffer2Mat(bufImg, convertImg);
+	cv::imshow("src", img);
+	cv::imshow("image", convertImg);
+	cv::waitKey(0);
+}
+
+int main()
+{
+
+	test01();
+
+	system("pause");
+	return 0;
+}
+
+// 运行程序: Ctrl + F5 或调试 >“开始执行(不调试)”菜单
+// 调试程序: F5 或调试 >“开始调试”菜单
+
+bool buffer2Mat(const MN_VisionImage::MS_ImageParam& _inImg, cv::Mat& _mat)
+{
+	uchar* pBuf = _inImg.m_data.get(); //获取图像数据首地址
+	int nW = _inImg.m_width;
+	int nH = _inImg.m_height;
+	int nChannel = _inImg.m_channels;
+
+	if (pBuf == nullptr || nW <= 1 || nH <= 1)
+	{
+		// LOG_ERROR("convert buffer to mat, input image error. \n");
+		return false;
+	}
+
+	if (_inImg.mImgType == MN_VisionImage::ME_ImageType::E_GRAY)
+	{
+		_mat = cv::Mat(nH, nW, CV_8UC1, pBuf);
+	}
+	else if (_inImg.mImgType == MN_VisionImage::ME_ImageType::E_RGBA)
+	{
+		_mat = cv::Mat(nH, nW, CV_8UC4, pBuf);
+	}
+	else
+	{
+		_mat = cv::Mat(nH, nW, CV_8UC3, pBuf);
+	}
+
+	if (_mat.data == nullptr || _mat.cols <= 1 || _mat.rows <= 1)
+	{
+		// LOG_ERROR("convert buffer to mat, convert image failed. \n");
+		return false;
+	}
+
+	return true;
+}
+
+
+// 0.3 * 0.3 - 12寸晶圆， 一次性识别9颗 -- 测试推理时间
+/*
+1. 芯片分类：正常，边缘，蓝膜
+2. 对于正常的芯片进行检测--针对划痕和脏污分两个模型/或者一个模型；
+3. 针对针测点检测 -- 传统算法；
+*/