noether.data.datasets.cfd.shapenet_car.zarr_dataset

Zarr-backed ShapeNet-Car dataset with chunk-based subsampling.

Attributes

logger

Classes

ZarrShapeNetCarDatasetConfig	Config for the Zarr-backed ShapeNet-Car dataset (root = converted Zarr store).
ZarrShapeNetCarDataset	ShapeNet-Car dataset that reads from a converted Zarr store.

Module Contents

noether.data.datasets.cfd.shapenet_car.zarr_dataset.logger

class noether.data.datasets.cfd.shapenet_car.zarr_dataset.ZarrShapeNetCarDatasetConfig(/, **data)

Bases: noether.data.datasets.cfd.zarr_aero_dataset.ZarrAeroDatasetConfig

Config for the Zarr-backed ShapeNet-Car dataset (root = converted Zarr store).

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

data (Any)

kind: str | None = 'noether.data.datasets.cfd.ZarrShapeNetCarDataset'

Kind of dataset to use.

class noether.data.datasets.cfd.shapenet_car.zarr_dataset.ZarrShapeNetCarDataset(dataset_config)

Bases: noether.data.datasets.cfd.zarr_aero_dataset.ZarrAeroDataset

ShapeNet-Car dataset that reads from a converted Zarr store.

Config-driven analogue of ShapeNetCarDataset where dataset_config.root points at the converted Zarr store. When the config’s num_surface_points / num_volume_points are given, the dataset chunk-subsamples at read time and returns exactly that many points per domain, so the pipeline’s PointSamplingSampleProcessor becomes a no-op.

Parameters:

dataset_config (ZarrShapeNetCarDatasetConfig) – ShapeNet-Car Zarr config; root is the Zarr store root and the num_* / sampling_seed / read_concurrency fields drive subsampling.

STATS_FILE: str = ''

split

design_ids

sample_info(idx)

Get information about a sample such as its store path and run name.

Parameters:

idx (int)

Return type:

dict[str, str | int | None]