mighty.utils.var_online.MeanOnlineLabels

class mighty.utils.var_online.MeanOnlineLabels(cls=<class 'mighty.utils.var_online.MeanOnlineBatch'>)

Keep track of population mean for each unique class label.

Parameters:

clstype, optional

The generator class of online mean: either MeanOnline or :class`MeanOnlineBatch`. Default: MeanOnlineBatch

Methods

__init__([cls])
activate(is_active)	Activates or deactivates the updates.
get_mean()
get_mean_labels()
labels()
reset()	Reset the mean and the count.
update(tensor, labels)	Update sample mean (and variance) from a batch of new values, split by labels.

activate(is_active: bool)

Activates or deactivates the updates.

Parameters:

is_activebool

New state.

get_mean()

Returns:

mean_sorted(C, V) torch.Tensor

Mean tensor for each of C unique class labels.

get_mean_labels()

Returns:

mean_sorted(C, V) torch.Tensor

Mean tensor for each of C unique class labels.

labels_sorted(C,) torch.Tensor

Class labels, associated with mean_sorted.

labels()

Returns:

list

Unique sorted class labels.

reset()

Reset the mean and the count.

update(tensor, labels)

Update sample mean (and variance) from a batch of new values, split by labels.

Parameters:

tensor(B, V) torch.Tensor

A tensor sample.

labels(B,) torch.Tensor

Batch labels.