hezar.data.datasets.image_captioning_dataset module

class hezar.data.datasets.image_captioning_dataset.ImageCaptioningDataset(config: ImageCaptioningDatasetConfig, split=None, preprocessor=None, **kwargs)

Bases: Dataset

required_backends: List[str | Backends] = [Backends.DATASETS]

class hezar.data.datasets.image_captioning_dataset.ImageCaptioningDatasetConfig(path: str | None = None, task: TaskType = TaskType.IMAGE2TEXT, max_size: int | float | None = None, hf_load_kwargs: dict | None = None, text_column: str = 'label', max_length: int | None = None)

Bases: DatasetConfig

Configuration class for image captioning datasets.

Parameters:

• path (str) – Path to the dataset.

• text_column (str) – Column name for text in the dataset.

• images_paths_column (str) – Column name for image paths in the dataset.

• max_length (int) – Maximum length of text.

images_paths_column = 'image_path'

max_length: int = None

name: str = 'image_captioning'

path: str = None

task: TaskType = 'image2text'

text_column: str = 'label'