Average#
- class ignite.metrics.Average(output_transform=<function Average.<lambda>>, device=device(type='cpu'), skip_unrolling=False)[source]#
Helper class to compute arithmetic average of a single variable.
update
must receive output of the form x.x can be a number or torch.Tensor.
Note
Number of samples is updated following the rule:
+1 if input is a number
+1 if input is a 1D torch.Tensor
+batch_size if input is an ND torch.Tensor. Batch size is the first dimension (shape[0]).
For input x being an ND torch.Tensor with N > 1, the first dimension is seen as the number of samples and is summed up and added to the accumulator: accumulator += x.sum(dim=0)
output_tranform
can be added to the metric to transform the output into the form expected by the metric.- Parameters
output_transform (Callable) – a callable that is used to transform the
Engine
’sprocess_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, device]) – specifies which device updates are accumulated on. Setting the metric’s device to be the same as your
update
arguments ensures theupdate
method is non-blocking. By default, CPU.skip_unrolling (bool) – specifies whether output should be unrolled before being fed to update method. Should be true for multi-output model, for example, if
y_pred
contains multi-ouput as(y_pred_a, y_pred_b)
Alternatively,output_transform
can be used to handle this.
Examples
For more information on how metric works with
Engine
, visit Attach Engine API.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.metrics.regression import * from ignite.utils 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 = Average() metric.attach(default_evaluator, 'avg') # Case 1. input is er data = torch.tensor([0, 1, 2, 3, 4]) state = default_evaluator.run(data) print(state.metrics['avg'])
2.0
metric = Average() metric.attach(default_evaluator, 'avg') # Case 2. input is a 1D torch.Tensor data = torch.tensor([ [0, 0, 0], [1, 1, 1], [2, 2, 2], [3, 3, 3] ]) state = default_evaluator.run(data) print(state.metrics['avg'])
tensor([1.5000, 1.5000, 1.5000], dtype=torch.float64)
metric = Average() metric.attach(default_evaluator, 'avg') # Case 3. input is a ND torch.Tensor data = [ torch.tensor([[0, 0, 0], [1, 1, 1]]), torch.tensor([[2, 2, 2], [3, 3, 3]]) ] state = default_evaluator.run(data) print(state.metrics['avg'])
tensor([1.5000, 1.5000, 1.5000], dtype=torch.float64)
Changed in version 0.5.1:
skip_unrolling
argument is added.Methods
Computes the metric based on its accumulated state.
- compute()[source]#
Computes the metric based on its 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 whencompleted()
is called. - Return type
Any
- Raises
NotComputableError – raised when the metric cannot be computed.