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

Calculates the root mean squared error.

RMSE=1Ni=1N(yixi)2\text{RMSE} = \sqrt{ \frac{1}{N} \sum_{i=1}^N \left(y_{i} - x_{i} \right)^2 }

where yiy_{i} is the prediction tensor and xix_{i} is ground true tensor.

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

  • 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. By default, metrics require the output as (y_pred, y) or {'y_pred': y_pred, 'y': y}.

  • device (Union[str, 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.


To use with Engine and process_function, simply attach the metric instance to the engine. The output of the engine’s process_function needs to be in the format of (y_pred, y) or {'y_pred': y_pred, 'y': y, ...}. If not, output_tranform can be added to the metric to transform the output into the form expected by the metric.

y_pred and y should have the same shape.

metric = RootMeanSquaredError()
metric.attach(default_evaluator, 'rmse')
preds = torch.Tensor([
    [1, 2, 4, 1],
    [2, 3, 1, 5],
    [1, 3, 5, 1],
    [1, 5, 1 ,11]
target = preds * 0.75
state =[[preds, target]])



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.