• Docs >
  • Module code >
  • ignite.contrib.metrics.regression.geometric_mean_relative_absolute_error

Source code for ignite.contrib.metrics.regression.geometric_mean_relative_absolute_error

from typing import Tuple, Union, cast

import torch

from ignite.contrib.metrics.regression._base import _BaseRegression
from ignite.exceptions import NotComputableError

[docs]class GeometricMeanRelativeAbsoluteError(_BaseRegression): r"""Calculates the Geometric Mean Relative Absolute Error. .. math:: \text{GMRAE} = \exp(\frac{1}{n}\sum_{j=1}^n \ln\frac{|A_j - P_j|}{|A_j - \bar{A}|}) where :math:`A_j` is the ground truth and :math:`P_j` is the predicted value. More details can be found in `Botchkarev 2018`__. - ``update`` must receive output of the form ``(y_pred, y)`` or ``{'y_pred': y_pred, 'y': y}``. - `y` and `y_pred` must be of same shape `(N, )` or `(N, 1)`. __ https://arxiv.org/abs/1809.03006 Parameters are inherited from ``Metric.__init__``. Args: output_transform: a callable that is used to transform the :class:`~ignite.engine.engine.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: 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. """ def reset(self) -> None: self._sum_y = 0.0 # type: Union[float, torch.Tensor] self._num_examples = 0 self._sum_of_errors = 0.0 # type: Union[float, torch.Tensor] def _update(self, output: Tuple[torch.Tensor, torch.Tensor]) -> None: y_pred, y = output self._sum_y += y.sum() self._num_examples += y.shape[0] y_mean = self._sum_y / self._num_examples numerator = torch.abs(y.view_as(y_pred) - y_pred) denominator = torch.abs(y.view_as(y_pred) - y_mean) self._sum_of_errors += torch.log(numerator / denominator).sum() def compute(self) -> float: if self._num_examples == 0: raise NotComputableError( "GeometricMeanRelativeAbsoluteError must have at least one example before it can be computed." ) return torch.exp(torch.mean(cast(torch.Tensor, self._sum_of_errors) / self._num_examples)).item()

© Copyright 2024, PyTorch-Ignite Contributors. Last updated on 01/11/2024, 12:22:53 PM.

Built with Sphinx using a theme provided by Read the Docs.