SSIM#
- class ignite.metrics.SSIM(data_range, kernel_size=(11, 11), sigma=(1.5, 1.5), k1=0.01, k2=0.03, gaussian=True, output_transform=<function SSIM.<lambda>>, device=device(type='cpu'), skip_unrolling=False)[source]#
Computes Structural Similarity Index Measure
update
must receive output of the form(y_pred, y)
. They have to be of the same type.Valid
torch.dtype
are the following: - on CPU: torch.float32, torch.float64. - on CUDA: torch.float16, torch.bfloat16, torch.float32, torch.float64.
- Parameters
data_range (Union[int, float]) – Range of the image. Typically,
1.0
or255
.kernel_size (Union[int, Sequence[int]]) – Size of the kernel. Default: (11, 11)
sigma (Union[float, Sequence[float]]) – Standard deviation of the gaussian kernel. Argument is used if
gaussian=True
. Default: (1.5, 1.5)k1 (float) – Parameter of SSIM. Default: 0.01
k2 (float) – Parameter of SSIM. Default: 0.03
gaussian (bool) –
True
to use gaussian kernel,False
to use uniform kerneloutput_transform (Callable) – A callable that is used to transform the
Engine
’sprocess_function
’s output into the form expected by the metric.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
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(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
andy
can be un-normalized or normalized image tensors. Depending on that, the user might need to adjustdata_range
.y_pred
andy
should have the same shape.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 = SSIM(data_range=1.0) metric.attach(default_evaluator, 'ssim') preds = torch.rand([4, 3, 16, 16]) target = preds * 0.75 state = default_evaluator.run([[preds, target]]) print(state.metrics['ssim'])
0.9218971...
New in version 0.4.2.
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.