The file structure for the dataset is
dataset/
│
├── train/
│ ├── blob2/
│ ├── blob3/
│ ├── ...
│ └── blob20/
│
└── test/
├── blob2/
├── blob3/
├── ...
└── blob20/
Each blob_i folder corresponds to a simulation run with i blobs or sinkers that
have a viscosity and density constrast relative to the surrounding material in
which they are sinking.
Each sample is stored as a Python dictionary (data_out) with the following fields:
surface_coords: (N, 2) array
Coordinates… See the full description on the dataset page:
https://huggingface.co/datasets/rheoformer/fem-dataset-rheology.
