带深度的坐标变化

#include <glad/glad.h>
#include <GLFW/glfw3.h>
#include <stb_image.h>

#include <glm/glm.hpp>
#include <glm/gtc/matrix_transform.hpp>
#include <glm/gtc/type_ptr.hpp>

#include <filesystem.h>
#include <shader_m.h>

#include <iostream>

using namespace std;

void framebuffer_size_callback(GLFWwindow* window, int width, int height);
void processInput(GLFWwindow *window);

// settings
const unsigned int SCR_WIDTH = 800;
const unsigned int SCR_HEIGHT = 600;

int main()
{
    // glfw: initialize and configure
    // ------------------------------
    glfwInit();
    glfwWindowHint(GLFW_CONTEXT_VERSION_MAJOR, 3);
    glfwWindowHint(GLFW_CONTEXT_VERSION_MINOR, 3);
    glfwWindowHint(GLFW_OPENGL_PROFILE, GLFW_OPENGL_CORE_PROFILE);

#ifdef __APPLE__
    glfwWindowHint(GLFW_OPENGL_FORWARD_COMPAT, GL_TRUE);
#endif

    // glfw window creation
    // --------------------
    GLFWwindow* window = glfwCreateWindow(SCR_WIDTH, SCR_HEIGHT, "LearnOpenGL", NULL, NULL);
    if (window == NULL)
    {
        std::cout << "Failed to create GLFW window" << std::endl;
        glfwTerminate();
        return -1;
    }
    glfwMakeContextCurrent(window);
    glfwSetFramebufferSizeCallback(window, framebuffer_size_callback);

    // glad: load all OpenGL function pointers
    // ---------------------------------------
    if (!gladLoadGLLoader((GLADloadproc)glfwGetProcAddress))
    {
        std::cout << "Failed to initialize GLAD" << std::endl;
        return -1;
    }

    // configure global opengl state
    // -----------------------------
    glEnable(GL_DEPTH_TEST);

    // build and compile our shader zprogram
    // ------------------------------------
    Shader ourShader("6.2.coordinate_systems.vs", "6.2.coordinate_systems.fs");

    // set up vertex data (and buffer(s)) and configure vertex attributes
    // ------------------------------------------------------------------
    float vertices[] = {
        -0.5f, -0.5f, -0.5f,  0.0f, 0.0f,
         0.5f, -0.5f, -0.5f,  1.0f, 0.0f,
         0.5f,  0.5f, -0.5f,  1.0f, 1.0f,
         0.5f,  0.5f, -0.5f,  1.0f, 1.0f,
        -0.5f,  0.5f, -0.5f,  0.0f, 1.0f,
        -0.5f, -0.5f, -0.5f,  0.0f, 0.0f,

        -0.5f, -0.5f,  0.5f,  0.0f, 0.0f,
         0.5f, -0.5f,  0.5f,  1.0f, 0.0f,
         0.5f,  0.5f,  0.5f,  1.0f, 1.0f,
         0.5f,  0.5f,  0.5f,  1.0f, 1.0f,
        -0.5f,  0.5f,  0.5f,  0.0f, 1.0f,
        -0.5f, -0.5f,  0.5f,  0.0f, 0.0f,

        -0.5f,  0.5f,  0.5f,  1.0f, 0.0f,
        -0.5f,  0.5f, -0.5f,  1.0f, 1.0f,
        -0.5f, -0.5f, -0.5f,  0.0f, 1.0f,
        -0.5f, -0.5f, -0.5f,  0.0f, 1.0f,
        -0.5f, -0.5f,  0.5f,  0.0f, 0.0f,
        -0.5f,  0.5f,  0.5f,  1.0f, 0.0f,

         0.5f,  0.5f,  0.5f,  1.0f, 0.0f,
         0.5f,  0.5f, -0.5f,  1.0f, 1.0f,
         0.5f, -0.5f, -0.5f,  0.0f, 1.0f,
         0.5f, -0.5f, -0.5f,  0.0f, 1.0f,
         0.5f, -0.5f,  0.5f,  0.0f, 0.0f,
         0.5f,  0.5f,  0.5f,  1.0f, 0.0f,

        -0.5f, -0.5f, -0.5f,  0.0f, 1.0f,
         0.5f, -0.5f, -0.5f,  1.0f, 1.0f,
         0.5f, -0.5f,  0.5f,  1.0f, 0.0f,
         0.5f, -0.5f,  0.5f,  1.0f, 0.0f,
        -0.5f, -0.5f,  0.5f,  0.0f, 0.0f,
        -0.5f, -0.5f, -0.5f,  0.0f, 1.0f,

        -0.5f,  0.5f, -0.5f,  0.0f, 1.0f,
         0.5f,  0.5f, -0.5f,  1.0f, 1.0f,
         0.5f,  0.5f,  0.5f,  1.0f, 0.0f,
         0.5f,  0.5f,  0.5f,  1.0f, 0.0f,
        -0.5f,  0.5f,  0.5f,  0.0f, 0.0f,
        -0.5f,  0.5f, -0.5f,  0.0f, 1.0f
    };
    unsigned int VBO, VAO;
    glGenVertexArrays(1, &VAO);
    glGenBuffers(1, &VBO);

    glBindVertexArray(VAO);

    glBindBuffer(GL_ARRAY_BUFFER, VBO);
    glBufferData(GL_ARRAY_BUFFER, sizeof(vertices), vertices, GL_STATIC_DRAW);

    // position attribute
    glVertexAttribPointer(0, 3, GL_FLOAT, GL_FALSE, 5 * sizeof(float), (void*)0);
    glEnableVertexAttribArray(0);
    // texture coord attribute
    glVertexAttribPointer(1, 2, GL_FLOAT, GL_FALSE, 5 * sizeof(float), (void*)(3 * sizeof(float)));
    glEnableVertexAttribArray(1);


    // load and create a texture 
    // -------------------------
    unsigned int texture1, texture2;
    // texture 1
    // ---------
    glGenTextures(1, &texture1);
    glBindTexture(GL_TEXTURE_2D, texture1);
    // set the texture wrapping parameters
    glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_WRAP_S, GL_REPEAT);
    glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_WRAP_T, GL_REPEAT);
    // set texture filtering parameters
    glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MIN_FILTER, GL_LINEAR);
    glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MAG_FILTER, GL_LINEAR);
    // load image, create texture and generate mipmaps
    int width, height, nrChannels;
    stbi_set_flip_vertically_on_load(true); // tell stb_image.h to flip loaded texture's on the y-axis.
	unsigned char *data = stbi_load("D:/Template/glfwtemplate/glfwtemplate/container.jpg", &width, &height, &nrChannels, 0);
    //unsigned char *data = stbi_load(FileSystem::getPath("resources/textures/container.jpg").c_str(), &width, &height, &nrChannels, 0);
    if (data)
    {
        glTexImage2D(GL_TEXTURE_2D, 0, GL_RGB, width, height, 0, GL_RGB, GL_UNSIGNED_BYTE, data);
        glGenerateMipmap(GL_TEXTURE_2D);
    }
    else
    {
        std::cout << "Failed to load texture" << std::endl;
    }
    stbi_image_free(data);
    // texture 2
    // ---------
    glGenTextures(1, &texture2);
    glBindTexture(GL_TEXTURE_2D, texture2);
    // set the texture wrapping parameters
    glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_WRAP_S, GL_REPEAT);
    glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_WRAP_T, GL_REPEAT);
    // set texture filtering parameters
    glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MIN_FILTER, GL_LINEAR);
    glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MAG_FILTER, GL_LINEAR);
    // load image, create texture and generate mipmaps
	data = stbi_load("D:/Template/glfwtemplate/glfwtemplate/awesomeface.png", &width, &height, &nrChannels, 0);
    //data = stbi_load(FileSystem::getPath("resources/textures/awesomeface.png").c_str(), &width, &height, &nrChannels, 0);
    if (data)
    {
        // note that the awesomeface.png has transparency and thus an alpha channel, so make sure to tell OpenGL the data type is of GL_RGBA
        glTexImage2D(GL_TEXTURE_2D, 0, GL_RGB, width, height, 0, GL_RGBA, GL_UNSIGNED_BYTE, data);
        glGenerateMipmap(GL_TEXTURE_2D);
    }
    else
    {
        std::cout << "Failed to load texture" << std::endl;
    }
    stbi_image_free(data);

    // tell opengl for each sampler to which texture unit it belongs to (only has to be done once)
    // -------------------------------------------------------------------------------------------
    ourShader.use();
    ourShader.setInt("texture1", 0);
    ourShader.setInt("texture2", 1);


    // render loop
    // -----------
    while (!glfwWindowShouldClose(window))
    {
        // input
        // -----
        processInput(window);

        // render
        // ------
        glClearColor(0.2f, 0.3f, 0.3f, 1.0f);
        glClear(GL_COLOR_BUFFER_BIT | GL_DEPTH_BUFFER_BIT); // also clear the depth buffer now!

        // bind textures on corresponding texture units
        glActiveTexture(GL_TEXTURE0);
        glBindTexture(GL_TEXTURE_2D, texture1);
        glActiveTexture(GL_TEXTURE1);
        glBindTexture(GL_TEXTURE_2D, texture2);

        // activate shader
        ourShader.use();

        // create transformations
        glm::mat4 model         = glm::mat4(1.0f); // make sure to initialize matrix to identity matrix first
        glm::mat4 view          = glm::mat4(1.0f);
        glm::mat4 projection    = glm::mat4(1.0f);
        model = glm::rotate(model, (float)glfwGetTime(), glm::vec3(0.5f, 1.0f, 0.0f));
        view  = glm::translate(view, glm::vec3(0.0f, 0.0f, -3.0f));
        projection = glm::perspective(glm::radians(45.0f), (float)SCR_WIDTH / (float)SCR_HEIGHT, 0.1f, 100.0f);
        // retrieve the matrix uniform locations
        unsigned int modelLoc = glGetUniformLocation(ourShader.ID, "model");
        unsigned int viewLoc  = glGetUniformLocation(ourShader.ID, "view");
        // pass them to the shaders (3 different ways)
        glUniformMatrix4fv(modelLoc, 1, GL_FALSE, glm::value_ptr(model));
        glUniformMatrix4fv(viewLoc, 1, GL_FALSE, &view[0][0]);
        // note: currently we set the projection matrix each frame, but since the projection matrix rarely changes it's often best practice to set it outside the main loop only once.
        ourShader.setMat4("projection", projection);

        // render box
        glBindVertexArray(VAO);
        glDrawArrays(GL_TRIANGLES, 0, 36);


        // glfw: swap buffers and poll IO events (keys pressed/released, mouse moved etc.)
        // -------------------------------------------------------------------------------
        glfwSwapBuffers(window);
        glfwPollEvents();
    }

    // optional: de-allocate all resources once they've outlived their purpose:
    // ------------------------------------------------------------------------
    glDeleteVertexArrays(1, &VAO);
    glDeleteBuffers(1, &VBO);

    // glfw: terminate, clearing all previously allocated GLFW resources.
    // ------------------------------------------------------------------
    glfwTerminate();
    return 0;
}

// process all input: query GLFW whether relevant keys are pressed/released this frame and react accordingly
// ---------------------------------------------------------------------------------------------------------
void processInput(GLFWwindow *window)
{
    if (glfwGetKey(window, GLFW_KEY_ESCAPE) == GLFW_PRESS)
        glfwSetWindowShouldClose(window, true);
}

// glfw: whenever the window size changed (by OS or user resize) this callback function executes
// ---------------------------------------------------------------------------------------------
void framebuffer_size_callback(GLFWwindow* window, int width, int height)
{
    // make sure the viewport matches the new window dimensions; note that width and 
    // height will be significantly larger than specified on retina displays.
    glViewport(0, 0, width, height);
}

### 深度学习中的坐标偏移概念 在深度学习尤其是目标检测任务中,坐标偏移(offset)是指相对于预定义锚框或网格单元预测的目标位置调整量。这种机制允许模型不仅能够识别物体的存在与否,还能精确指出其确切的位置。 #### 锚框与坐标偏移 为了提高检测精度,在许多现代框架如YOLO、SSD等中引入了锚框的概念。这些预先设定好的矩形框覆盖整个输入图片的不同比例和大小。对于每一个可能含有物体的候选区域,除了类别标签之外还会输出四个数值来表示该区域内真实边界框相对应于当前默认尺寸的变化情况——即所谓的“坐标偏移”。这四个参数通常对应着中心点坐标的横向纵向位移以及宽度高度的比例缩放因子[^1]。 ```python def calculate_offset(predicted_box, anchor_box): """ 计算给定预测框与锚框之间的坐标偏移 参数: predicted_box (tuple): 预测得到的真实边界框(x_center, y_center, width, height) anchor_box (tuple): 默认设置的锚框(x_center, y_center, width, height) 返回: tuple: 坐标偏移(tx, ty, tw, th) """ tx = (predicted_box[0] - anchor_box[0]) / anchor_box[2] ty = (predicted_box[1] - anchor_box[1]) / anchor_box[3] tw = math.log(predicted_box[2] / anchor_box[2]) th = math.log(predicted_box[3] / anchor_box[3]) return (tx, ty, tw, th) ``` 通过这种方式,即使是在不同尺度下存在的多个实例也可以在同一张特征图上被有效地区分出来并准确定位到它们各自的具体位置[^2]。 当对象位于图像边缘附近时,可能会出现一些特殊情况。例如,如果对象中心非常接近区域的边界,则可能导致难以准确划分所属负责预测的责任方格;此时某些架构会选择忽略那些与其他责任区重叠程度较高的部分以减少混淆[^3]。
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值