GeometricMeanRelativeAbsoluteError

class ignite.contrib.metrics.regression.GeometricMeanRelativeAbsoluteError(output_transform=<function Metric.<lambda>>, device=device(type='cpu'))

Calculates the Geometric Mean Relative Absolute Error.

$$\text{GMRAE} = \exp(\frac{1}{n}\sum_{j=1}^n \ln\frac{|A_j - P_j|}{|A_j - \bar{A}|})$$

where $A_j$ is the ground truth, $P_j$ is the predicted value and :math: bar{A} is the mean of the ground truth.

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).

Parameters are inherited from Metric.__init__.

Warning

Current implementation of GMRAE stores all input data (output and target) as tensors before computing the metric. This can potentially lead to a memory error if the input data is larger than available RAM.

In distributed configuration, all stored data (output and target) is mutually collected across all processes using all gather collective operation. This can potentially lead to a memory error.

Compute method compute the metric on zero rank process only and final result is broadcasted to all processes.

Parameters

• 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.

Examples

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 format of (y_pred, y) or {'y_pred': y_pred, 'y': y, ...}.

from collections import OrderedDict

import torch
from torch import nn, optim

from ignite.engine import *
from ignite.handlers import *
from ignite.metrics import *
from ignite.utils import *
from ignite.contrib.metrics.regression import *
from ignite.contrib.metrics import *

# create default evaluator for doctests

def eval_step(engine, batch):
    return batch

default_evaluator = Engine(eval_step)

# create default optimizer for doctests

param_tensor = torch.zeros([1], requires_grad=True)
default_optimizer = torch.optim.SGD([param_tensor], lr=0.1)

# create default trainer for doctests
# as handlers could be attached to the trainer,
# each test must define his own trainer using `.. testsetup:`

def get_default_trainer():

    def train_step(engine, batch):
        return batch

    return Engine(train_step)

# create default model for doctests

default_model = nn.Sequential(OrderedDict([
    ('base', nn.Linear(4, 2)),
    ('fc', nn.Linear(2, 1))
]))

manual_seed(666)

metric = GeometricMeanRelativeAbsoluteError()
metric.attach(default_evaluator, 'gmare')
y_true = torch.Tensor([0, 1, 2, 3, 4, 5])
y_pred = y_true * 0.75
state = default_evaluator.run([[y_pred, y_true]])
print(state.metrics['gmare'])

0.0...

Methods

compute	Computes the metric based on it's accumulated state.
reset	Resets the metric to it's initial state.

compute()

Computes the metric based on it’s accumulated state.

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

Returns

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

Any

Raises

NotComputableError – raised when the metric cannot be computed.

reset()

Resets the metric to it’s initial state.

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

Return type

None