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'))[source]#
Computes Structual Similarity Index Measure
- 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, torch.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.
Example:
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, ...}
.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.def process_function(engine, batch): # ... return y_pred, y engine = Engine(process_function) metric = SSIM(data_range=1.0) metric.attach(engine, "ssim")
New in version 0.4.2.
Methods
Computes the metric based on it's accumulated state.
Resets the metric to it's initial state.
Updates the metric's state using the passed batch output.
- compute()[source]#
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 whencompleted()
is called. - Return type
Any
- Raises
NotComputableError – raised when the metric cannot be computed.
- reset()[source]#
Resets the metric to it’s initial state.
By default, this is called at the start of each epoch.
- Return type
- update(output)[source]#
Updates the metric’s state using the passed batch output.
By default, this is called once for each batch.
- Parameters
output (Sequence[torch.Tensor]) – the is the output from the engine’s process function.
- Return type