带标注信息的交通信号灯识别数据集，可识别左转灯，红绿黄灯，识别率82.88%，支持yolo，coco json，pascal voc xml格式

带标注信息的交通信号灯识别数据集可识别左转灯红绿黄灯识别率82.88%支持yolococo jsonpascal voc xml格式模型训练指标参数数据集拆分训练集701张图验证集199张图测试集100张图预处理自动定向应用调整大小拉伸到1280*731增强未增强数据集标签Traffic LightRed LightGreen LightLeft turnYellow Light数据集图片和标注信息示例数据集下载yolo26:https://download.csdn.net/download/pbymw8iwm/92792555yolo v12:https://download.csdn.net/download/pbymw8iwm/92792560yolo v11:https://download.csdn.net/download/pbymw8iwm/92792561yolo v9:https://download.csdn.net/download/pbymw8iwm/92792556yolo v8:https://download.csdn.net/download/pbymw8iwm/92792558yolo v7:https://download.csdn.net/download/pbymw8iwm/92792557yolo v5:https://download.csdn.net/download/pbymw8iwm/92792553yolo darknet:https://download.csdn.net/download/pbymw8iwm/92792559coco json:https://download.csdn.net/download/pbymw8iwm/92792562pascal voc xml:https://download.csdn.net/download/pbymw8iwm/92792554YOLO模型训练下载数据集之后解压到当前文件夹然后将 我的仓库 https://gitcode.com/pbymw8iwm/YOLOProject里的训练模型脚本复制到文件夹下假设你使用的是yolov8来训练你就用 python train_yolov8.py注意请根据你的GPU能力来适当调整训练参数比如训练batchpatienceworkers以及模型类型如果你的GPU硬件条件限制可以联系作者进行付费模型训练部分模型只需要一杯奶茶钱​模型下载模型验证测试情况验证测试代码#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(best.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 ./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(YOLOv Inference, annotated_image) # 等待按键退出 cv2.waitKey(0) # 关闭所有 OpenCV 窗口 cv2.destroyAllWindows()推理结果{predictions: [{x: 192,y: 136,width: 18,height: 16,confidence: 0.916,class: Left turn,class_id: 1,detection_id: 3ce53424-be29-4758-8629-d3357156fabd},{x: 306,y: 140.5,width: 20,height: 19,confidence: 0.915,class: Red Light,class_id: 2,detection_id: 549efeea-103e-4605-b2b5-fb77fa74b56e},{x: 342,y: 142.5,width: 18,height: 17,confidence: 0.912,class: Left turn,class_id: 1,detection_id: ed6fcf80-53d8-4f4d-bd61-36ce64642d37},{x: 155.5,y: 135,width: 17,height: 16,confidence: 0.882,class: Red Light,class_id: 2,detection_id: 93f66caa-4885-46a0-9f3a-23c7d4d5da0b}]}