aac_datasets.datasets.macs module¶

class MACS(

root: str | Path | None = None,

subset: 'full' = 'full',

download: bool = False,

transform: Callable[[MACSItem], Any] | None = None,

verbose: int = 0,

force_download: bool = False,

verify_files: bool = False,

*,

clean_archives: bool = True,

flat_captions: bool = False,

)[source]¶

Bases: AACDataset[MACSItem]

Unofficial MACS PyTorch dataset.

Dataset folder tree¶

{root}
└── MACS
    ├── audio
    │    └── (3930 wav files, ~13GB)
    ├── LICENCE.txt
    ├── MACS.yaml
    ├── MACS_competence.csv
    └── tau_meta
        ├── fold1_evaluate.csv
        ├── fold1_test.csv
        ├── fold1_train.csv
        └── meta.csv

CARD : ClassVar[MACSCard] = <aac_datasets.datasets.functional.macs.MACSCard object>¶

property download : bool¶

get_annotator_id_to_competence_dict() → dict[int, float][source]¶

Get annotator to competence dictionary.

get_competence(

annotator_id: int,

) → float[source]¶

Get competence value for a specific annotator id.

property root : str¶

property sr : int¶

property subset : 'full'¶

class MACSItem[source]¶

Bases: TypedDict

Dataclass representing a single MACS item.

annotators_ids : List[str]¶

audio : Tensor¶

captions : List[str]¶

competences : List[float]¶

dataset : str¶

duration : float¶

fname : str¶

identifier : str¶

index : int¶

scene_label : str¶

sr : int¶

subset : Literal['full']¶

tags : List[List[str]]¶