Mosaic

class easypl.callbacks.mixers.mosaic.Mosaic(on_batch: bool = True, n_mosaics: Union[int, List[int]] = 4, num_workers: int = 1, p: float = 0.5, domen: str = 'classification')

Callback for mosaic data operations

on_batch

If True generate samples from batch otherwise from dataset.

Type: bool

p

Mix probability.

Type: float

num_workers

Number of workers for mixing operation.

Type: int

n_mosaics

Number of mosaics. If it’s list, then number of mosaic will be selected from this list.

Type: Union[int, List[int]]

domen

Name of task, in which will be mixed samples. Available: [“classification, segmentation”].

Type: str

mix(sample1: Dict, sample2: Dict) → Dict

Mosaic mix method for two samples.

sample1

Sample of batch, which will be sampled with samples from sample2.

Type: Dict

sample2

Samples from batch or dataset.

Type: Dict

Returns: Mixed sample.
Return type: Dict