emmi.pipeline.batch_processors.moment_normalization

Classes

MomentNormalizationBatchProcessor

Normalizes a value with its mean and standard deviation (i.e., its moments).

Module Contents

class emmi.pipeline.batch_processors.moment_normalization.MomentNormalizationBatchProcessor(items, mean, std)

Bases: ksuit.data.pipeline.BatchProcessor

Normalizes a value with its mean and standard deviation (i.e., its moments).

Initializes the MomentNormalizationPostCollator

Parameters:

• items (list[str]) – the position items to normalize.

• mean (collections.abc.Sequence[float]) – the mean of the value.

• std (collections.abc.Sequence[float]) – the standard deviation of the value.

items

mean_tensor

std_tensor

denormalize(key, value)

Inverts the normalization from the __call__ method of a single item in the batch.

Parameters:

• key (str) – The name of the item.

• value (torch.Tensor) – The value of the item.

Returns:

The same name and the denormalized value.

Return type:

(key, value)