class ignite.metrics.Average(output_transform=<function Average.<lambda>>, device=device(type='cpu'))[source]#

Helper class to compute arithmetic average of a single variable.

  • update must receive output of the form x.

  • x can be a number or torch.Tensor.


Number of samples is updated following the rule:

  • +1 if input is a number

  • +1 if input is a 1D torch.Tensor

  • +batch_size if input is an ND torch.Tensor. Batch size is the first dimension (shape[0]).

For input x being an ND torch.Tensor with N > 1, the first dimension is seen as the number of samples and is summed up and added to the accumulator: accumulator += x.sum(dim=0)


evaluator = ...

custom_var_mean = Average(output_transform=lambda output: output['custom_var'])
custom_var_mean.attach(evaluator, 'mean_custom_var')

state =
# state.metrics['mean_custom_var'] -> average of output['custom_var']
  • output_transform (Callable) – a callable that is used to transform the Engine’s process_function’s output into the form expected by the metric. This can be useful if, for example, you have a multi-output model and you want to compute the metric with respect to one of the outputs.

  • device (Union[str, torch.device]) – specifies which device updates are accumulated on. Setting the metric’s device to be the same as your update arguments ensures the update method is non-blocking. By default, CPU.



Computes the metric based on it's accumulated state.


Computes the metric based on it’s accumulated state.

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


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



NotComputableError – raised when the metric cannot be computed.