Compose

class mmcv.transforms.Compose(transforms: Dict | Callable[[Dict], Dict] | Sequence[Dict | Callable[[Dict], Dict]])

Compose multiple transforms sequentially.

Parameters:

transforms (list[dict | callable]) – Sequence of transform object or config dict to be composed.

Examples

>>> pipeline = [
>>>     dict(type='Compose',
>>>         transforms=[
>>>             dict(type='LoadImageFromFile'),
>>>             dict(type='Normalize')
>>>         ]
>>>     )
>>> ]

transform(results: Dict) → Dict | None

Call function to apply transforms sequentially.

Parameters:

results (dict) – A result dict contains the results to transform.

Returns:

Transformed results.

Return type:

dict or None