RunningAverage#

class ignite.metrics.RunningAverage(src=None, alpha=0.98, output_transform=None, epoch_bound=True, device=None)[source]#

Compute running average of a metric or the output of process function.

Parameters

src (Optional[Metric]) – input source: an instance of Metric or None. The latter corresponds to engine.state.output which holds the output of process function.
alpha (float) – running average decay factor, default 0.98
output_transform (Optional[Callable]) – a function to use to transform the output if src is None and corresponds the output of process function. Otherwise it should be None.
epoch_bound (bool) – whether the running average should be reset after each epoch (defaults to True).
device (Optional[Union[device, str]]) – specifies which device updates are accumulated on. Should be None when src is an instance of Metric, as the running average will use the src’s device. Otherwise, defaults to CPU. Only applicable when the computed value from the metric is a tensor.

Examples

accuracy = Accuracy()
metric = RunningAverage(accuracy)
metric.attach(default_evaluator, 'running_avg_accuracy')

@default_evaluator.on(Events.ITERATION_COMPLETED)
def log_running_avg_metrics():
    print(default_evaluator.state.metrics['running_avg_accuracy'])

y_true = [torch.Tensor(y) for y in [[0], [1], [0], [1], [0], [1]]]
y_pred = [torch.Tensor(y) for y in [[0], [0], [0], [1], [1], [1]]]

state = default_evaluator.run(zip(y_pred, y_true))

0
98
98039...
98079...
96117...
96195...

metric = RunningAverage(output_transform=lambda x: x.item())
metric.attach(default_evaluator, 'running_avg_accuracy')

@default_evaluator.on(Events.ITERATION_COMPLETED)
def log_running_avg_metrics():
    print(default_evaluator.state.metrics['running_avg_accuracy'])

y = [torch.Tensor(y) for y in [[0], [1], [0], [1], [0], [1]]]

state = default_evaluator.run(y)

0
020000...
019600...
039208...
038423...
057655...

Methods

`attach`	Attaches current metric to provided engine.
`compute`	Computes the metric based on it's accumulated state.
`reset`	Resets the metric to it's initial state.
`update`	Updates the metric's state using the passed batch output.

attach(engine, name, _usage=<ignite.metrics.metric.EpochWise object>)[source]#

Attaches current metric to provided engine. On the end of engine’s run, engine.state.metrics dictionary will contain computed metric’s value under provided name.

Parameters

engine (Engine) – the engine to which the metric must be attached
name (str) – the name of the metric to attach
usage – the usage of the metric. Valid string values should be ignite.metrics.metric.EpochWise.usage_name (default) or ignite.metrics.metric.BatchWise.usage_name.
_usage (Union[str, MetricUsage]) –

Return type

None

Examples

metric = ...
metric.attach(engine, "mymetric")

assert "mymetric" in engine.run(data).metrics

assert metric.is_attached(engine)

Example with usage:

metric = ...
metric.attach(engine, "mymetric", usage=BatchWise.usage_name)

assert "mymetric" in engine.run(data).metrics

assert metric.is_attached(engine, usage=BatchWise.usage_name)

compute()[source]#

Computes the metric based on it’s accumulated state.

By default, this is called at the end of each epoch.

Returns

the actual quantity of interest. However, if a Mapping is returned, it will be (shallow) flattened into engine.state.metrics when completed() is called.

Return type

Any

Raises

NotComputableError – raised when the metric cannot be computed.

required_output_keys: Optional[Tuple] = None#

reset()[source]#

Resets the metric to it’s initial state.

By default, this is called at the start of each epoch.

Return type: None

update(output)[source]#

Updates the metric’s state using the passed batch output.

By default, this is called once for each batch.

Parameters: output (Sequence) – the is the output from the engine’s process function.
Return type: None