class ignite.metrics.Rouge(variants=None, multiref='average', alpha=0, output_transform=<function Rouge.<lambda>>, device=device(type='cpu'))[source]#

Calculates the Rouge score for multiples Rouge-N and Rouge-L metrics.

More details can be found in Lin 2004.

  • update must receive output of the form (y_pred, y) or {'y_pred': y_pred, 'y': y}.

  • y_pred (list(list(str))) must be a sequence of tokens.

  • y (list(list(list(str))) must be a list of sequence of tokens.

  • variants (Optional[Sequence[Union[str, int]]]) – set of metrics computed. Valid inputs are “L” and integer 1 <= n <= 9.

  • multiref (str) – reduces scores for multi references. Valid values are “best” and “average” (default: “average”).

  • alpha (float) – controls the importance between recall and precision (alpha -> 0: recall is more important, alpha -> 1: precision is more important)

  • 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.


For more information on how metric works with Engine, visit Attach Engine API.

from ignite.metrics import Rouge

m = Rouge(variants=["L", 2], multiref="best")

candidate = "the cat is not there".split()
references = [
    "the cat is on the mat".split(),
    "there is a cat on the mat".split()

m.update(([candidate], [references]))

{'Rouge-L-P': 0.6, 'Rouge-L-R': 0.5, 'Rouge-L-F': 0.5, 'Rouge-2-P': 0.5, 'Rouge-2-R': 0.4, 'Rouge-2-F': 0.4}

New in version 0.4.5.

Changed in version 0.4.7: update method has changed and now works on batch of inputs.



Computes the metric based on it's accumulated state.


Resets the metric to it's initial state.


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


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.


Resets the metric to it’s initial state.

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

Return type



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

By default, this is called once for each batch.


output (Tuple[Sequence[Sequence[Any]], Sequence[Sequence[Sequence[Any]]]]) – the is the output from the engine’s process function.

Return type