# MRS-TB3-Mindspore **Repository Path**: Mutil-Unmanned-System/mrs-tb3-mindspore ## Basic Information - **Project Name**: MRS-TB3-Mindspore - **Description**: 基于mindspore的无人小车平台 - **Primary Language**: Unknown - **License**: Not specified - **Default Branch**: master - **Homepage**: None - **GVP Project**: No ## Statistics - **Stars**: 0 - **Forks**: 0 - **Created**: 2025-12-14 - **Last Updated**: 2025-12-15 ## Categories & Tags **Categories**: Uncategorized **Tags**: None ## README # 前言目标：在ubuntu20.04的noetic的ros环境下，利用mindyolo进行对已知大小的二维码进行识别并进行定位。环境：mindspore == 2.0.0, cuda-nvcc == 11.6, cuda-version == 11.6, cudatoolkit == 11.6, cudnn ==8.0.0. # 1 利用conda安装mindspore和cuda环境首先安在NVIDIA驱动，可以使用nvidia-smi命令后再安装下列环境。 ```bash conda create --name mindspore python=3.7 source activate mindspore conda install mindspore=2.0.0 -c mindspore -c conda-forge conda install -c nvidia cuda-nvcc=11.6 conda install cudatoolkit=11.6 -c https://mirrors.ustc.edu.cn/anaconda/pkgs/main/ conda install cudnn=8.8.0 -c https://mirrors.ustc.edu.cn/anaconda/pkgs/main/ export PATH=/home/robot/anaconda3/envs/mindspore/bin:$PATH export LD_LIBRARY_PATH=/home/robot/anaconda3/pkgs/cudatoolkit-11.6.2-hfc3e2af_12/lib:$PATH \$LD_LIBRARY_PATH ``` 以上环境安装成功后，可能会有一些其他库也需要安装，运行的时候会弹出报错，利用pip或者conda安装就好。 # 2 安装mindyolo目标检测算法我这里推荐源码安装，因为能安装最新的版本，目前我使用的是0.3.0版本。 ```bash git clone https://github.com/mindspore-lab/mindyolo.git cd mindyolo pip install -r requirements.txt # 安装依赖，注意版本 pip install -e . ``` # 3 制作数据 ## 3.1 采集数据在ros环境下创建mindyolo功能包，并在其src文件下创建capture_image.cpp文件，将下列代码写入： ```cpp #include #include #include #include #include #include #include // 全局变量，用于存储上次保存的图像文件名中的整数部分 int last_saved_index = 0; // 获取上次保存的图像文件名中的整数部分 void get_last_saved_index(const std::string& filename) { std::ifstream file(filename); std::string line; if (file.is_open()) { while (std::getline(file, line)) { // 解析文件名，获取整数部分 // 假设文件名格式为 xxxxxxx.jpg，其中 xxxxxxx 表示整数部分 std::size_t found = line.find_last_of("/"); std::size_t found2 = line.find_last_of("."); std::string index_str = line.substr(found + 1, found2 - found - 1); int index = std::stoi(index_str); if (index > last_saved_index) { last_saved_index = index; } } file.close(); } } void pic_callback(const sensor_msgs::ImageConstPtr &img_msg) { ros::Time time = img_msg->header.stamp; std::string filename_prefix = "/home/robot/catkin_ws/src/mindyolo/VOC2007/JEPGImages/"; // 获取上次保存的图像文件名中的整数部分 get_last_saved_index(filename_prefix + "last_saved.txt"); // 构建新的文件名 std::string filename_suffix = std::to_string(last_saved_index + 1); std::string filename = filename_prefix + filename_suffix + ".jpg"; cv_bridge::CvImageConstPtr ptr; ptr = cv_bridge::toCvCopy(img_msg, "bgr8"); printf("%s\n", filename.c_str()); cv::imwrite(filename, ptr->image); // 将本次保存的整数部分写入文件，以备下次使用 std::ofstream last_saved_file(filename_prefix + "last_saved.txt"); last_saved_file << filename_suffix; last_saved_file.close(); } int main(int argc, char **argv) { ros::init(argc, argv, "img_save"); ros::NodeHandle n; ros::Subscriber sub_image = n.subscribe(argv[1], 1, pic_callback); ros::spin(); return 0; } ``` 记得在CMakeLists.txt文件里添加编译环境。 ```bash add_executable(capture_image src/capture_image.cpp) target_link_libraries(capture_image ${catkin_LIBRARIES} ${OpenCV_LIBS}) ``` 回到ros的catkin_ws工作空间使用catkin_make即可。 ```bash catkin_make source ~/catkin_ws/devel/setup.sh rosrun mindyolo capture_image /camera/left/image_raw #/camera/left/image_raw是你照相机的话题 ``` > 运行后就可以在目录“/home/robot/catkin_ws/src/mindyolo/VOC2007/JEPGImages/"获得照片。 > 需要更改目录的话，请更改capture_image.cpp代码里的filename_prefix。 ## 3.2 使用labelimg标注数据安装labelimg ```bash pip install labelimg -i https://pypi.tuna.tsinghua.edu.cn/simple ``` 然后准备我们需要打标注的数据集。这里我建议新建一个名为VOC2007的文件夹，里面创建一个名为JPEGImages的文件夹存放我们需要打标签的图片文件；再创建一个名为Annotations存放标注的标签文件；最后创建一个名为 predefined_classes.txt 的txt文件来存放所要标注的类别名称。 VOC2007的目录结构为： ```bash ├── VOC2007 │├── JPEGImages 存放需要打标签的图片文件 │├── Annotations 存放标注的标签文件 │├── predefined_classes.txt 定义自己要标注的所有类别 ``` 具体标注操作方式详见：[https://blog.csdn.net/didiaopao/article/details/119808973?spm=1001.2014.3001.5506](https://blog.csdn.net/didiaopao/article/details/119808973?spm=1001.2014.3001.5506) ## 3.3 生成voc数据集在目录/home/robot/mindyolo/examples/code/VOC2007下创建getvoc.py文件： ```python #getvoc.py #-*- coding:utf-8 -*- import os import random import numpy as np xml_file_path = "/home/robot/mindyolo/examples/code/VOC2007/Annotations" target_path = "/home/robot/mindyolo/examples/code/VOC2007/ImageSets/Main" # perception trainval = 0.9 # (num of trainval set) / (num of all samples) train = 0.8 # (num of train set) / (num of trainval set) def listdir(path, list_name): for file in os.listdir(path): file_path = os.path.join(path, file) if os.path.isdir(file_path): listdir(file_path, list_name) elif os.path.splitext(file_path)[1] == '.xml': tmp = os.path.splitext(file_path)[0] # Extract the numeric part of the file name file_name = os.path.basename(tmp) numeric_part = ''.join(filter(str.isdigit, file_name)) list_name.append(int(numeric_part)) file_list = [] listdir(xml_file_path, file_list) num_of_files = len(file_list) num_of_trainval = int(trainval * num_of_files) num_of_train = int(train * num_of_trainval) # divide samples in trainval and test trainval_list = np.sort(random.sample(file_list, num_of_trainval)) test_list = np.sort(np.setdiff1d(file_list, trainval_list)) # divide trainval in train and value train_list = np.sort(random.sample(list(trainval_list), num_of_train)) value_list = np.sort(np.setdiff1d(trainval_list, train_list)) print(trainval_list) print(test_list) print(train_list) print(value_list) # Save lists to text files file = open(target_path + '/trainval.txt', 'w') for var in trainval_list: file.write(str(var) + '\n') file.close() file = open(target_path + '/test.txt', 'w') for var in test_list: file.write(str(var) + '\n') file.close() file = open(target_path + '/train.txt', 'w') for var in train_list: file.write(str(var) + '\n') file.close() file = open(target_path + '/val.txt', 'w') for var in value_list: file.write(str(var) + '\n') file.close() ``` > 注意： > 我采集的图片是放在了ros工作空间下，这里将数据集复制到了mindyolo下，使用的时候注意文件路径就好，例如xml_file_path和target_path需要修改。 > 并且，需要在VOC2007文件目录下创建ImageSets文件夹和ImageSets/main文件夹，因为我的程序里面没有直接创建，需要注意一下。运行脚本就可以在同目录下生成VOC文件了 ```bash python3 getvoc.py ``` ## 3.4 转为yolo格式在/home/robot/mindyolo/examples/code目录下（和刚刚的VOC2007一个目录就行），这个code目录是我自己创建的，git官方库是没有的，这里是为了方便管理，这是我的code目录 ```bash ├── convert_shwd2yolo.py ├── SHWD │ ├── annotations │ ├── images │ ├── labels │ ├── train.cache.npy │ ├── train.txt │ └── val.txt ├── VOC2007 │ ├── Annotations │ ├── getvoc.py │ ├── ImageSets │ ├── JPEGImages │ └── predefined_classes.txt ├── yolov7-tiny_300e_mAP375-d8972c94.ckpt └── yolov7-tiny_shwd.yaml ``` 创建voc数据转化yolo数据脚本convert_shwd2yolo.py ```python #convert_shwd2yolo.py import os from pathlib import Path import argparse import shutil import xml.etree.ElementTree as ET import collections import json from tqdm import tqdm category_set = ['tb0', 'tb1', 'tb2', 'tb3', 'tb4'] coco = dict() coco['images'] = [] coco['type'] = 'instances' coco['annotations'] = [] coco['categories'] = [] category_item_id = 0 annotation_id = 0 image_index = 0 def addCatItem(name): global category_item_id category_item = collections.OrderedDict() category_item['supercategory'] = 'none' category_item['id'] = category_item_id category_item['name'] = name coco['categories'].append(category_item) category_item_id += 1 def addImgItem(image_id, size): file_name = str(image_id).zfill(8) + '.jpg' if not size['width']: raise Exception('Could not find width tag in xml file.') if not size['height']: raise Exception('Could not find height tag in xml file.') image_item = collections.OrderedDict() image_item['file_name'] = file_name image_item['width'] = size['width'] image_item['height'] = size['height'] image_item['id'] = image_id coco['images'].append(image_item) def addAnnoItem(image_id, category_id, bbox): global annotation_id annotation_item = collections.OrderedDict() annotation_item['segmentation'] = [] # segmentation seg = [] # left_top seg.append(bbox[0]) seg.append(bbox[1]) # left_bottom seg.append(bbox[0]) seg.append(bbox[1] + bbox[3]) # right_bottom seg.append(bbox[0] + bbox[2]) seg.append(bbox[1] + bbox[3]) # right_top seg.append(bbox[0] + bbox[2]) seg.append(bbox[1]) annotation_item['segmentation'].append(seg) annotation_item['area'] = bbox[2] * bbox[3] annotation_item['iscrowd'] = 0 annotation_item['image_id'] = image_id annotation_item['bbox'] = bbox annotation_item['category_id'] = category_id annotation_item['id'] = annotation_id annotation_item['ignore'] = 0 annotation_id += 1 coco['annotations'].append(annotation_item) def xxyy2xywhn(size, box): dw = 1. / (size[0]) dh = 1. / (size[1]) x = (box[0] + box[1]) / 2.0 - 1 y = (box[2] + box[3]) / 2.0 - 1 w = box[1] - box[0] h = box[3] - box[2] x = x * dw w = w * dw y = y * dh h = h * dh x = round(x, 6) w = round(w, 6) y = round(y, 6) h = round(h, 6) return x, y, w, h def xml2txt(xml_path, txt_path): in_file = open(xml_path, encoding='utf-8') out_file = open(txt_path, 'w', encoding='utf-8') tree = ET.parse(in_file) root = tree.getroot() size = root.find('size') w = int(size.find('width').text) h = int(size.find('height').text) for obj in root.iter('object'): difficult = obj.find('difficult').text cls = obj.find('name').text if cls not in category_set or int(difficult) == 1: continue cls_id = category_set.index(cls) xmlbox = obj.find('bndbox') x1, x2, y1, y2 = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text), float(xmlbox.find('ymax').text)) # clip x2, y2 to normal range if x2 > w: x2 = w if y2 > h: y2 = h # xyxy2xywhn bbox = (x1, x2, y1, y2) bbox = xxyy2xywhn((w, h), bbox) out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bbox]) + '\n') def xml2json(image_index, xml_path): bndbox = dict() size = dict() size['width'] = None size['height'] = None tree = ET.parse(xml_path) root = tree.getroot() if root.tag != 'annotation': raise Exception('pascal voc xml root element should be annotation, rather than {}'.format(root.tag)) # elem format: , , ,