带标注的施工工人防护服安全帽识别数据集，六千多张原始图，识别率83.8%，可识别是否穿戴防护服，安全帽，支持yolo，coco json，pascal voc xml 格式

带标注的施工工人防护服安全帽识别数据集六千多张原始图识别率83.8%可识别是否穿戴防护服安全帽支持yolococo jsonpascal voc xml 格式标签helmet, no_helmet, no_vest, vest分别是戴安全帽未戴安全帽 未穿防护服穿防护服数据集拆分训练集4860图片验证集1251图片测试集660图片预处理没有进行任何预处理步骤。增强未进行任何增强数据集图片和标注信息模型训练和验证测试代码完整的代码仓库在 https://gitcode.net/pbymw8iwm/Python_299818直接将下载的数据集解压放到本地后将这段代码放到数据集目录里模型训练代码#如果存在版本兼容问题使用:pip install --upgrade ultralytics from ultralytics import YOLO # 加载预训练的 YOLOv8 模型 model YOLO(yolov8n.pt) # 训练模型 results model.train( datadata.yaml, # 数据集的配置文件路径 epochs100, # 训练的轮数 imgsz640 # 输入图像的大小 ) # 评估模型 metrics model.val()测试验证代码#需要安装pip install ultralytics from ultralytics import YOLO import cv2 # 加载训练好的 YOLO .pt 模型 model YOLO(trained_yolov8n.pt) # 替换为你实际的 .pt 模型文件路径 # 定义要测试的图片路径 image_path path/to/your/image.jpg # 替换为你实际的图片文件路径 # 使用模型对图片进行预测 results model(image_path) # 获取预测结果 for result in results: # 获取绘制了检测框的图片 annotated_image result.plot() # 显示图片 cv2.imshow(YOLOv8 Inference, annotated_image) # 等待按键退出 cv2.waitKey(0) # 关闭所有 OpenCV 窗口 cv2.destroyAllWindows()模型测试验证推理结果{predictions: [{x: 1592.5,y: 881.5,width: 813,height: 1451,confidence: 0.873,class: no_helmet,class_id: 1,detection_id: bd2d72f6-e3b0-4bf4-9c78-cd072d091285},{x: 2977,y: 1797,width: 642,height: 928,confidence: 0.864,class: no_vest,class_id: 2,detection_id: 1603fd9a-1567-4f89-802b-4e0fc7e4bf30},{x: 1607.5,y: 2313.5,width: 1399,height: 1885,confidence: 0.733,class: no_vest,class_id: 2,detection_id: 3b37b4ca-7fa2-429b-8902-3ab6ed5fa27f}]}推理结果{predictions: [{x: 92.5,y: 263,width: 131,height: 254,confidence: 0.871,class: vest,class_id: 3,detection_id: d241463c-c1c9-4484-b04d-1ce732172360},{x: 96,y: 79,width: 70,height: 120,confidence: 0.858,class: helmet,class_id: 0,detection_id: 98237eb8-4933-4169-be50-3b8fda93778c},{x: 312,y: 255.5,width: 118,height: 237,confidence: 0.841,class: vest,class_id: 3,detection_id: 2fbb9adf-7cb9-4e41-95ca-1bfe24b3074c},{x: 314.5,y: 71.5,width: 67,height: 115,confidence: 0.84,class: helmet,class_id: 0,detection_id: f188ca33-d2da-4325-920d-a607d8c00920}]}数据集下载yolo26:https://download.csdn.net/download/pbymw8iwm/92759318yolo12:https://download.csdn.net/download/pbymw8iwm/92759311yolo11:https://download.csdn.net/download/pbymw8iwm/92759312yolo 9:https://download.csdn.net/download/pbymw8iwm/92759312yolo8:https://download.csdn.net/download/pbymw8iwm/92759315yolo7:https://download.csdn.net/download/pbymw8iwm/92759316yolo5:https://download.csdn.net/download/pbymw8iwm/92759317yolo darknethttps://download.csdn.net/download/pbymw8iwm/92759322coco jsonhttps://download.csdn.net/download/pbymw8iwm/92759325pascal voc xmlhttps://download.csdn.net/download/pbymw8iwm/92759319