aggregate_metrics

aggregate_metrics(outputs: list[dict[str, float | torch.Tensor]], exclude_keys: Container[str] = {'_', 'a', 'c', 'f', 'm', 'n', 'o', 't'}) → dict[str, float]

Aggregate the output of validate_step at the end of the epoch.

Parameters:

• outputs (list[dict[str, float | torch.Tensor]]) – A list of outputs of Learner.validate_step().

• exclude_keys (Container[str]) – Keys to ignore. These will not be aggregated and will not be included in the output. Defaults to {‘conf_mat’}.

Returns:

Dict with aggregated values.

Return type:

dict[str, float]