Skip to content

moving_average

[ allennlp.training.moving_average ]


NamedParameter#

NamedParameter = Tuple[str, torch.Tensor]

MovingAverage Objects#

class MovingAverage(Registrable):
 | def __init__(self, parameters: Iterable[NamedParameter]) -> None

Tracks a moving average of model parameters.

default_implementation#

default_implementation = "exponential"

apply#

 | def apply(self, num_updates: Optional[int] = None)

Update the moving averages based on the latest values of the parameters.

assign_average_value#

 | def assign_average_value(self) -> None

Replace all the parameter values with the averages. Save the current parameter values to restore later.

restore#

 | def restore(self) -> None

Restore the backed-up (non-average) parameter values.

ExponentialMovingAverage Objects#

class ExponentialMovingAverage(MovingAverage):
 | def __init__(
 |     self,
 |     parameters: Iterable[NamedParameter],
 |     decay: float = 0.9999,
 |     numerator: float = 1.0,
 |     denominator: float = 10.0
 | ) -> None

Create shadow variables and maintain exponential moving average for model parameters.

Registered as a MovingAverage with name "exponential".

Parameters

  • parameters : Iterable[Tuple[str, Parameter]]
    The parameters whose averages we'll be tracking.

    In a typical AllenNLP configuration file, this argument does not get an entry under the "moving_average", it gets passed in separately. - decay : float, optional (default = 0.9999)
    The decay rate that will be used if num_updates is not passed (and that will be used as an upper bound if num_updates is passed). - numerator : float, optional (default = 1.0)
    The numerator used to compute the decay rate if num_updates is passed. - denominator : float, optional (default = 10.0)
    The denominator used to compute the decay rate if num_updates is passed.

apply#

 | def apply(self, num_updates: Optional[int] = None) -> None

Apply exponential moving average to named_parameters if specified, or we will apply this to all the trainable parameters of the model.

The optional num_updates parameter allows one to tweak the decay rate dynamically. If passed, the actual decay rate used is:

`min(decay, (numerator + num_updates) / (denominator + num_updates))`

(This logic is based on the Tensorflow exponential moving average https://www.tensorflow.org/api_docs/python/tf/train/ExponentialMovingAverage)