feat: Add configurable CSV output filename for evaluation results

- Introduced a new command-line argument `--csv_name` to allow custom CSV filename for evaluation results
- Updated `compute_all()` function to use the dynamically specified CSV filename
- Improved flexibility of evaluation script by enabling users to specify output file name
- Maintained existing logging and error handling mechanisms

code/evaluation/evaluation.py

@@ -30,6 +30,7 @@ parser.add_argument('--pred_path', type=str,
 parser.add_argument('--name_list', type=str, default='broken_bullet_name.txt', help='names of models to be evaluated, if you want to evaluate the whole dataset, please set it as all_names.txt')
 parser.add_argument('--nsample', type=int, default=50000, help='point batch size')
 parser.add_argument('--regen', default = False, action="store_true", help = 'regenerate feature curves')
+parser.add_argument('--csv_name', type=str, default='eval_results.csv', help='csv file name')
 args = parser.parse_args()
 
 def distance_p2p(points_src, normals_src, points_tgt, normals_tgt):
@@ -230,9 +231,9 @@ def compute_all():
         
         # 保存结果
         df = pd.DataFrame(results)
-        df.to_csv('eval_results.csv', index=False)
+        df.to_csv(args.csv_name, index=False)
         
-        logger.info(f"Evaluation completed. Results saved to {os.path.abspath('eval_results.csv')}")
+        logger.info(f"Evaluation completed. Results saved to {os.path.abspath(args.csv_name)}")
         
     except Exception as e:
         logger.error(f"Error in compute_all: {str(e)}")

code/pre_processing/.gitignore

@@ -0,0 +1,3 @@
+training_data/
+raw_input/
+Bin/

code/pre_processing/Dockerfile

@@ -0,0 +1,23 @@
+# 基础版本
+FROM ubuntu:20.04
+
+# 基本设置
+ENV DEBIAN_FRONTEND=noninteractive 
+ENV TZ=Asia/Shanghai
+
+# 安装基础包
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    cmake \
+    python3 \
+    python3-pip \
+    libboost-all-dev \
+    git \
+    vim \
+    && rm -rf /var/lib/apt/lists/*
+
+# 工作目录
+WORKDIR /app
+
+# 启动终端
+CMD ["/bin/bash"]

code/pre_processing/FeatureSample/FeatureSampleConfig.cpp

@@ -0,0 +1,94 @@
+#include "FeatureSampleConfig.h"
+#include <iostream>
+
+namespace MeshLib {
+
+FeatureSampleConfig FeatureSampleConfig::FromCommandLine(int argc, char** argv) {
+    cxxopts::Options options("FeatureSample", "Feature sampling for 3D meshes");
+    
+    options.add_options()
+        ("i,input", "input mesh (obj/off format)", cxxopts::value<std::string>())
+        ("f,feature", "input feature file (fea format)", cxxopts::value<std::string>())
+        ("p,pointcloud", "input pointcloud", cxxopts::value<std::string>())
+        ("pf", "face of input pointcloud", cxxopts::value<std::string>())
+        ("o,output", "output mesh/points", cxxopts::value<std::string>())
+        ("k,mask", "output mask file", cxxopts::value<std::string>())
+        ("fs", "feature samples", cxxopts::value<int>())
+        ("ns", "non-feature samples", cxxopts::value<int>())
+        ("m,mode", "processing mode", cxxopts::value<int>())
+        ("c,color", "use coloring", cxxopts::value<int>())
+        ("mp", "max patches per cluster", cxxopts::value<int>())
+        ("cot", "use cotangent weight", cxxopts::value<int>())
+        ("s,sigma", "position noise sigma", cxxopts::value<double>())
+        ("sn", "normal noise sigma", cxxopts::value<double>())
+        ("csg", "generate csg tree", cxxopts::value<int>())
+        ("convex", "is first layer convex", cxxopts::value<int>())
+        ("r,repairturn", "repair turn vertex", cxxopts::value<int>())
+        ("verbose", "verbose level", cxxopts::value<int>())
+        ("strict", "strict mode")
+        ("repairtree", "repair tree feature")
+        ("h,help", "print help");
+
+    auto result = options.parse(argc, argv);
+    
+    if (result.count("help")) {
+        std::cout << options.help() << std::endl;
+        exit(0);
+    }
+
+    FeatureSampleConfig config;
+
+    // 检查必需参数
+    if (!result.count("m") || !result.count("i") || !result.count("o")) {
+        throw std::runtime_error("Missing required parameters");
+    }
+
+    // 设置文件路径
+    config.files.input_mesh = result["i"].as<std::string>();
+    config.files.output_file = result["o"].as<std::string>();
+    if (result.count("f")) config.files.input_feature = result["f"].as<std::string>();
+    if (result.count("p")) config.files.input_pointcloud = result["p"].as<std::string>();
+    if (result.count("pf")) config.files.input_pointcloud_face = result["pf"].as<std::string>();
+    if (result.count("k")) config.files.output_mask = result["k"].as<std::string>();
+
+    // 设置采样参数
+    if (result.count("fs")) config.sampling.feature_samples = result["fs"].as<int>();
+    if (result.count("ns")) config.sampling.nonfeature_samples = result["ns"].as<int>();
+    if (result.count("s")) config.sampling.sigma = result["s"].as<double>();
+    if (result.count("sn")) config.sampling.sigma_normal = result["sn"].as<double>();
+    if (result.count("cot")) config.sampling.use_cotweight = result["cot"].as<int>();
+
+    // 设置处理选项
+    config.processing.mode = result["m"].as<int>();
+    if (result.count("c")) config.processing.use_color = result["c"].as<int>();
+    if (result.count("mp")) config.processing.max_patches = result["mp"].as<int>();
+    if (result.count("csg")) config.processing.generate_csg = result["csg"].as<int>();
+    if (result.count("convex")) config.processing.is_convex = result["convex"].as<int>();
+    if (result.count("r")) config.processing.repair_turn = result["r"].as<int>();
+    if (result.count("verbose")) config.processing.verbose = result["verbose"].as<int>();
+    if (result.count("strict")) config.processing.strict_mode = true;
+    if (result.count("repairtree")) config.processing.repair_tree = true;
+
+    return config;
+}
+
+bool FeatureSampleConfig::Validate() const {
+    // 检查文件路径
+    if (files.input_mesh.empty() || files.output_file.empty()) {
+        return false;
+    }
+
+    // 检查采样参数
+    if (sampling.feature_samples < 0 || sampling.nonfeature_samples < 0) {
+        return false;
+    }
+
+    // 检查处理模式
+    if (processing.mode != 0 && processing.mode != 1) {
+        return false;
+    }
+
+    return true;
+}
+
+} // namespace MeshLib 

code/pre_processing/FeatureSample/FeatureSampleConfig.h

@@ -0,0 +1,48 @@
+#pragma once
+#include <string>
+#include "cxxopts.hpp"
+
+namespace MeshLib {
+
+class FeatureSampleConfig {
+public:
+    // 文件路径
+    struct FilePaths {
+        std::string input_mesh;          // 输入网格文件
+        std::string input_feature;       // 输入特征文件
+        std::string input_pointcloud;    // 输入点云文件
+        std::string input_pointcloud_face; // 输入点云面片文件
+        std::string output_file;         // 输出文件
+        std::string output_mask;         // 输出掩码文件
+    } files;
+
+    // 采样参数
+    struct SamplingParams {
+        int feature_samples = 10000;     // 特征边采样点数
+        int nonfeature_samples = 40000;  // 非特征面采样点数
+        double sigma = 0.0;              // 位置噪声标准差
+        double sigma_normal = 0.0;       // 法向噪声标准差
+        bool use_cotweight = false;      // 是否使用余切权重
+    } sampling;
+
+    // 处理选项
+    struct ProcessingOptions {
+        int mode = 1;                    // 处理模式 (0:标准化, 1:特征采样)
+        bool use_color = false;          // 是否使用颜色
+        int max_patches = -1;            // 每个颜色簇的最大面片数
+        bool generate_csg = false;       // 是否生成CSG树
+        bool is_convex = false;          // 第一层是否为凸的
+        bool repair_turn = true;         // 是否修复转角顶点
+        bool repair_tree = false;        // 是否修复树特征
+        bool strict_mode = false;        // 是否使用严格模式
+        int verbose = 0;                 // 详细输出级别
+    } processing;
+
+    // 从命令行参数解析配置
+    static FeatureSampleConfig FromCommandLine(int argc, char** argv);
+    
+    // 验证配置是否有效
+    bool Validate() const;
+};
+
+} // namespace MeshLib 

code/pre_processing/README.md

@@ -10,11 +10,15 @@ Please first download the prepared ABC dataset from [BaiduYun](https://pan.baidu
 
 **\[Optional\]** If you want to split the models and generate the correponding *.fea files from the raw ABC dataset, please first put the *.yml and *.obj files in folder _abc_data_ (make sure that file in different formats share the same prefix). Install the PyYAML package via:
 
-        $ pip install PyYAML        
+```
+$ pip install PyYAML
+```
 
 and run:
 
-        $ python split_and_gen_fea.py
+```
+$ python split_and_gen_fea.py
+```
 
 You will find the split models and *.fea files in _raw_input_.
 
@@ -22,39 +26,55 @@ You will find the split models and *.fea files in _raw_input_.
 
 Please first install the Boost and eigen3 library:
 
-        $ sudo apt install libboost-all-dev
+```
-        $ sudo apt install libeigen3-dev
+$ sudo apt install libboost-all-dev
+$ sudo apt install libeigen3-dev
+```
+
 Then run:
 
-        $ cd PATH_TO_NH-REP/code/pre_processing
+```
-        $ mkdir build && cd build
+$ cd PATH_TO_NH-REP/code/pre_processing
-        $ cmake ..
+$ mkdir build && cd build
-        $ make
+$ cmake ..
+$ make
+```
 
 You can generate the training data:
 
-        $ cd ..
+```
-        $ python gen_training_data_yaml.py
+$ cd ..
+$ python gen_training_data_yaml.py
+```
 
 The generated training data can be found in _training_data_ folder.
 
 If you do not have a yaml file and want to generate sample points from meshes, you can prepare the *.fea file as sharp feature curves of the meshes, then run:
 
-        $ python gen_training_data_mesh.py
+```
+$ python gen_training_data_mesh.py
+```
 
 Please make sure that you set 'in_path' in _gen_training_data_yaml.py_ and _gen_training_data_mesh.py_ as the path containing the *.fea files.
 
-
 When patch decomposition is conducted (like model 00007974_5), there will be *fixtree.obj and *fixtree.fea in _training_data_, which can be used for generating point samples in later round:
 
-        $ python gen_training_data_yaml.py -r
+```
+$ python gen_training_data_yaml.py -r
+```
+
+or
 
-or 
+```
+$ python gen_training_data_mesh.py -r
+```
 
-        $ python gen_training_data_mesh.py -r
-        
 You can find the generated training data of the decomposed patch in _training_data_repair_. By default we only decompose one patch and it is enough for most models. But if you find *fixtree.obj and *fixtree.fea in _training_data_repair_, that means that more patches need to decomposed. There are two ways to achieve this. First, you can copy _training_data_repair./*fixtree.obj_ and _training_data_repair./*fixtree.fea_ to _training_data_, and re-run 'python gen_training_data_yaml.py -r', until enough patches are decomposed (i.e. *.conf files can be found in _training_data_repair_). Another way is to decompose all patches at once, to achieve this, simple uncomment the following line in _FeatureSample/helper.cpp_:
 
 https://github.com/guohaoxiang/NH-Rep/blob/42ae22bf8fc3f1b4f9f5592443c29aafe86905bd/code/pre_processing/FeatureSample/helper.cpp#L722
 
 After that, rebuild the executable files, and re-run 'python gen_training_data_yaml.py' and 'python gen_training_data_yaml.py -r'. There will be generated training data in _training_data_repair_.
+
+
+docker build -t brep_pre_processing:v1 .
+docker run -it --name brep_processor -v ~/NH-Rep/code/pre_processing:/app brep_pre_processing:v1

idea.md

@@ -3,29 +3,35 @@
 ## 1. 数据噪声鲁棒性增强
 
 ### 研究问题
+
 现有的方法对数据噪声有一定的鲁棒性，但仍有改进空间。研究如何进一步提高算法对噪声的鲁棒性。
 
 ### 创新点
+
 - **噪声建模**：引入更复杂的噪声模型（高斯噪声、椒盐噪声等），测试算法在不同噪声条件下的表现
 - **对抗训练**：使用对抗生成网络（GAN）或自监督学习方法，增强模型对噪声的鲁棒性
 - **正则化技术**：探索新的正则化方法（平滑损失、总变差正则化等），减少噪声对模型的影响
 - **多尺度处理**：结合多尺度分析，处理不同层次的几何细节，提高对局部噪声的鲁棒性
 
 ### 预期成果
+
 开发一种更鲁棒的隐式转换方法，能够在存在噪声的情况下保持较高的转换质量。
 
 ## 2. 特征保留与细节增强
 
 ### 研究问题
+
 虽然现有的方法在保留尖锐特征方面表现出色，但仍然有提升空间。研究如何更好地捕捉和保留B-Rep模型中的细小特征。
 
 ### 创新点
+
 - **特征检测改进**：引入更先进的特征检测算法（基于深度学习的边缘检测、曲率估计等）
 - **特征增强损失**：设计专门针对特征保留的损失函数（如特征角度误差FAE的加权版本）
 - **多分辨率表示**：结合多分辨率表示方法，动态调整特征区域的采样密度
 - **后处理优化**：研究等值面提取后的后处理方法，增强特征的清晰度和准确性
 
 ### 预期成果
+
 提出一种能够在保持整体几何精度的同时，更好保留尖锐特征和细节的隐式转换方法。
 
 [... 其他部分类似格式 ...]
@@ -33,26 +39,30 @@
 # 实施建议
 
 1. **选择具体切入点**
+
    - 根据兴趣和资源选择研究重点
    - 每个方向都有其独特的挑战和机遇
-
 2. **文献综述**
+
    - 进行广泛的文献综述
    - 了解当前研究进展和存在的问题
    - 找到研究空白点
-
 3. **实验设计**
+
    - 设计合理的实验方案
    - 选择合适的数据集
    - 设定评估指标
    - 搭建实验环境
-
 4. **代码实现**
+
    - 使用合适的编程工具（Python、PyTorch、TensorFlow等）
    - 参考开源项目
    - 确保代码原创性
-
 5. **论文撰写**
+
    - 撰写详细的毕业论文
    - 包含完整的研究内容
-   - 突出创新点和贡献
+   - 突出创新点和贡献
+
+
+1.15