mighty.utils.var_online.VarianceOnline

class mighty.utils.var_online.VarianceOnline(tensor=None)

Welford’s online algorithm for population mean and variance estimation.

Methods

__init__([tensor])
activate(is_active)	Activates or deactivates the updates.
get_mean()	Returns:
get_mean_std([unbiased])	Return mean and std of all samples.
reset()	Reset the mean and the count.
update(tensor)	Update sample mean (and variance) from a batch of new values.

activate(is_active)

Activates or deactivates the updates.

Parameters:

is_activebool

New state.

get_mean()

Returns:

torch.Tensor

The mean of all tensors.

get_mean_std(unbiased=True)

Return mean and std of all samples.

Parameters:

unbiasedbool, optional

Biased (False) or unbiased (True) variance estimate. Default: True

Returns:

meantorch.Tensor

The mean of all samples.

stdtorch.Tensor

The std of all samples.

reset()

Reset the mean and the count.

update(tensor)

Update sample mean (and variance) from a batch of new values.

Parameters:

tensortorch.Tensor

Next tensor sample.