Wi-Re/SFBC_dataset_I

该数据集包含用于论文《Symmetric basis convolutions for learning lagrangian fluid mechanics》（发表于ICLR 2024）的第一个测试案例（1D compressible SPH）的数据。数据集以hdf5文件格式存储，每个实验一个文件，文件中包含配置参数和每一帧的模拟数据。对于2D测试案例，数据集有预定义的训练/测试分割，而1D和3D案例则没有。此外，还提供了一个简单的Jupyter笔记本示例，用于加载和可视化数据集，并运行一个简单的训练示例。

This dataset contains the data for the first test case (1D compressible SPH) for the paper Symmetric basis convolutions for learning lagrangian fluid mechanics (Published at ICLR 2024). The data is stored in hdf5 files, with each file representing an experiment, containing configuration parameters and separate storage groups for each simulation frame. Each frame contains information for all fluid particles and all potentially relevant information. The 2D test cases have a pre-defined test/train split, whereas the 1D and 3D cases do not contain such a split. The dataset also includes a simple Jupyter notebook (Visualizer.ipynb) for loading and visualizing the dataset, and performing simple training to learn SPH summation-based density for different basis functions.