MaximumMeanDiscrepancy#
- class ignite.metrics.MaximumMeanDiscrepancy(var=1.0, output_transform=<function MaximumMeanDiscrepancy.<lambda>>, device=device(type='cpu'), skip_unrolling=False)[source]#
Calculates the mean of maximum mean discrepancy (MMD).
where is the batch size, and and are feature vectors sampled from and , respectively. is the Gaussian RBF kernel.
This metric computes the MMD for each batch and takes the average.
More details can be found in Gretton et al. 2012.
update
must receive output of the form(x, y)
.x
andy
are expected to be in the same shape .
- Parameters
var (float) – the bandwidth of the kernel. Default: 1.0
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. By default, this metric requires the output as(x, y)
.device (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
To use with
Engine
andprocess_function
, simply attach the metric instance to the engine. The output of the engine’sprocess_function
needs to be in the format of(x, y)
. If not,output_tranform
can be added to the metric to transform the output into the form expected by the metric.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 = MaximumMeanDiscrepancy() metric.attach(default_evaluator, "mmd") x = torch.tensor([[-0.80324818, -0.95768364, -0.03807209], [-0.11059691, -0.38230813, -0.4111988], [-0.8864329, -0.02890403, -0.60119252], [-0.68732452, -0.12854739, -0.72095073], [-0.62604613, -0.52368328, -0.24112842]]) y = torch.tensor([[0.0686768, 0.80502737, 0.53321717], [0.83849465, 0.59099726, 0.76385441], [0.68688272, 0.56833803, 0.98100778], [0.55267761, 0.13084654, 0.45382906], [0.0754253, 0.70317304, 0.4756805]]) state = default_evaluator.run([[x, y]]) print(state.metrics["mmd"])
1.072697639465332
Changed in version 0.5.1:
skip_unrolling
argument is added.Methods
Computes the metric based on its accumulated state.
Resets the metric to its initial state.
Updates the metric's state using the passed batch output.
- 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.