noether.data.pipeline.batch_processors.moment_normalization¶

Classes¶

MomentNormalizationBatchProcessor

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

Module Contents¶

class noether.data.pipeline.batch_processors.moment_normalization.MomentNormalizationBatchProcessor(items, mean, std)¶

Bases: noether.data.pipeline.batch_processor.BatchProcessor

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

Example:

processor = MomentNormalizationBatchProcessor(
    items=['velocity', 'pressure'],
    mean=[1.0, 2.0],
    std=[0.1, 0.2],
)
batch = {
    'velocity': torch.tensor([[.., ..], [.., ..]]),
    'pressure': torch.tensor([[.., ..], [.., ..]]),
}
normalized_batch = processor(batch)
# normalized_batch['velocity'] will be tensor([[.., ..], [.., ..]])
# normalized_batch['pressure'] will be tensor([[.., ..], [.., ..]])

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)