一个统一的视觉建模库，支持从分类到检索的全流程研究与部署。
DORAEMON: A Unified Library for Visual Object Modeling and Representation Learning at Scale
- 基于YAML配置实现多任务统一工作流，支持分类、检索与度量学习。
- 集成1000+预训练模型，在ImageNet-1K等数据集上达到或超越基线性能。
- 一键导出ONNX/HuggingFace，适合科研快速验证与工业落地应用。
DORAEMON 是一个开源的 PyTorch 库，统一了跨多种规模的视觉物体建模与表征学习。单一 YAML 驱动的工作流涵盖分类、检索与度量学习；通过与 timm 兼容的接口，提供超过 1000 个预训练主干网络，以及模块化损失函数、增强策略和分布式训练工具。可复现的训练配方在 ImageNet-1K、MS-Celeb-1M 与 Stanford Online Products 数据集上达到或超过参考结果，且支持一键导出至 ONNX 或 HuggingFace，实现研究与部署的无缝衔接。通过整合数据集、模型与训练技术，DORAEMON 为视觉识别与表征学习提供了可扩展的实验基础，高效推动研究成果向实际应用转化。代码仓库见 https://github.com/wuji3/DORAEMON。
原文摘要 · Abstract (English)
DORAEMON is an open-source PyTorch library that unifies visual object modeling and representation learning across diverse scales. A single YAML-driven workflow covers classification, retrieval and metric learning; more than 1000 pretrained backbones are exposed through a timm-compatible interface, together with modular losses, augmentations and distributed-training utilities. Reproducible recipes match or exceed reference results on ImageNet-1K, MS-Celeb-1M and Stanford online products, while one-command export to ONNX or HuggingFace bridges research and deployment. By consolidating datasets, models, and training techniques into one platform, DORAEMON offers a scalable foundation for rapid experimentation in visual recognition and representation learning, enabling efficient transfer of research advances to real-world applications. The repository is available at https://github.com/wuji3/DORAEMON.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。