OpenTO/OpenOAT
收藏Hugging Face2025-05-08 更新2025-11-01 收录
下载链接：
https://hf-mirror.com/datasets/OpenTO/OpenOAT
下载链接
链接失效反馈官方服务：
资源简介：
OpenOAT是一个大规模的有限元分析问题数据集，包含使用SIMP优化器解决的随机问题。数据集分为三个部分：2M个样本的预训练数据，未标记边界条件和负载；700K个样本的标记数据，包含边界条件、负载和体积分数的标记；以及15K个样本的测试数据，用于测试，不包含在前两个数据集中。数据集遵循cc-by-nc-nd-4.0许可。
OpenOAT is a massive dataset of random FEA problems solved using a SIMP optimizer, which includes three parts: pre-training data with 2M sample topologies without labeled boundary condition and loads, labeled data with 700K samples that also exist in the pre-training data with labeled boundary conditions, loads, and volume fraction, and test data with 15K labeled samples not present in the prior datasets for testing. The dataset is licensed under cc-by-nc-nd-4.0.
提供机构：
OpenTO
