nerfbaselines¶
- class nerfbaselines.Cameras(*args, **kwargs)[source]¶
Bases:
GenericCameras
[ndarray
],Protocol
- class nerfbaselines.Method(*, checkpoint: str | None = None, train_dataset: Dataset | None = None, config_overrides: Dict[str, Any] | None = None)[source]¶
Bases:
Protocol
- abstract classmethod get_method_info() MethodInfo [source]¶
Get method info needed to initialize the datasets.
- Returns:
Method info.
- abstract get_train_embedding(index: int) ndarray | None [source]¶
Get the embedding for the given image index.
- Parameters:
index – Image index.
- Returns:
Image embedding.
- abstract optimize_embeddings(dataset: Dataset, embeddings: Sequence[ndarray] | None = None) Iterable[OptimizeEmbeddingsOutput] [source]¶
Optimize embeddings for each image in the dataset.
- Parameters:
dataset – Dataset.
embeddings – Optional initial embeddings.
- abstract render(cameras: Cameras, *, embeddings: Sequence[ndarray] | None = None, options: RenderOptions | None = None) Iterable[RenderOutput] [source]¶
Render images.
- Parameters:
cameras – Cameras.
embeddings – Optional image embeddings.
- class nerfbaselines.MethodInfo[source]¶
Bases:
TypedDict
- name: Required[str]¶
- required_features: FrozenSet[Literal['color', 'points3D_xyz', 'points3D_rgb']]¶
- supported_camera_models: FrozenSet¶
- supported_outputs: Tuple[str | RenderOutputType, ...]¶
- class nerfbaselines.ModelInfo[source]¶
Bases:
TypedDict
- batch_size: int¶
- eval_batch_size: int¶
- hparams: Dict[str, Any]¶
- loaded_checkpoint: str | None¶
- loaded_step: int | None¶
- name: Required[str]¶
- num_iterations: Required[int]¶
- required_features: FrozenSet[Literal['color', 'points3D_xyz', 'points3D_rgb']]¶
- supported_camera_models: FrozenSet¶
- supported_outputs: Tuple[str, ...]¶