HidingMyIdentity/IRIS

IRIS数据集是一个全面的真实世界数据集，旨在研究工业机器人环境中物体检测的模拟到真实转移。该数据集包含508张标注图像，涵盖32种机械部件，分布在四种不同的工业场景中。此外，还提供了合成数据生成所需的3D模型、背景和材料，以及两个示例合成训练集（各4000张图像）和预训练的YOLO11m模型。数据集结构清晰，包含真实测试集、合成训练集和资源文件夹，支持COCO和YOLO格式的标注。

The IRIS Dataset is a comprehensive real-world dataset designed to study sim-to-real transfer for object detection in industrial robotic environments. It includes 508 annotated images of 32 mechanical components across four distinct industrial scenes. The dataset also provides assets for synthetic data generation, two example synthetic training sets (4000 images each), and pre-trained YOLO11m model checkpoints. The dataset is well-organized, featuring a real test set, synthetic train sets, and assets folders, with annotations available in COCO and YOLO formats.