estimators

Classes:

Name	Description
`Estimator`	Defines an interface for estimating noise components from input values.
`PatchEstimator`	Defines an interface for estimating noise components using non-overlapping 2D convolutions over input image(s).

Estimator ¶

Bases: Generic[ModuleT, OptionalParameterizationT, OptionalMaskerT], Module

Defines an interface for estimating noise components from input values.

Estimators should return a tensor of a broadcastable shape to the input tensor.

Parameters:

Name	Type	Description	Default
`module` ¶	`ModuleT`	The module to use to estimate the unparameterized noise component.	required
`target_parameter` ¶	`str`	The name of the parameter to pass the input tensor as to the `module`.	required
`parameterization` ¶	`OptionalParameterizationT`	The optional parameterization to apply to the output of `module`.	`None`
`masker` ¶	`OptionalMaskerT`	The optional masker to apply to the output of the `parameterization`.	`None`

Added in version 0.37.0.

Methods:

Name	Description
`__call__`	Estimate noise components from input values.
`forward`	Estimate noise components from input values.
`reset_parameters`	Reinitialize parameters and buffers.

call ¶

__call__(
    input: Tensor,
    noise_mask: Tensor | None = None,
    **kwargs: Any,
) -> tuple[torch.Tensor, torch.Tensor | None]

__call__(
    input: Tensor,
    noise_mask: Tensor | None = None,
    **kwargs: Any,
) -> tuple[torch.Tensor, torch.Tensor | None]

__call__(
    input: Tensor,
    noise_mask: Tensor | None = None,
    **kwargs: Any,
) -> tuple[torch.Tensor, torch.Tensor | None]

__call__(
    input: Tensor,
    noise_mask: Tensor | None = None,
    **kwargs: Any,
) -> tuple[torch.Tensor, torch.Tensor | None]

Estimate noise components from input values.

Parameters:

Name	Type	Description	Default
`input` ¶	`Tensor`	The tensor to estimate noise components from.	required
`noise_mask` ¶	`Tensor \| None`	An optional mask tensor to use to select a subset of the elements of the estimated standard deviations for computing a mask to apply to the input. If `None`, the mask is computed over all of the estimated standard deviations.	`None`
`kwargs` ¶	`Any`	Additional keyword arguments to `module`.	required

Returns:

Type	Description
`tuple[torch.Tensor, torch.Tensor \| None]`	A tuple containing the estimated noise components and an input mask if there is a `masker`.

forward ¶

forward(
    input: Tensor,
    noise_mask: Tensor | None = None,
    **kwargs: Any,
) -> tuple[torch.Tensor, torch.Tensor | None]

Estimate noise components from input values.

Parameters:

Name	Type	Description	Default
`input` ¶	`Tensor`	The tensor to estimate noise components from.	required
`noise_mask` ¶	`Tensor \| None`	An optional mask tensor to use to select a subset of the elements of the estimated standard deviations for computing a mask to apply to the input. If `None`, the mask is computed over all of the estimated standard deviations.	`None`
`kwargs` ¶	`Any`	Additional keyword arguments to `module`.	required

Returns:

Type	Description
`tuple[torch.Tensor, torch.Tensor \| None]`	A tuple containing the estimated noise components and an input mask if there is a `masker`.

reset_parameters ¶

reset_parameters() -> None

Reinitialize parameters and buffers.

This method is useful for initializing tensors created on the meta device.

PatchEstimator ¶

Bases: Estimator[Conv2d, OptionalParameterizationT, OptionalMaskerT]

Defines an interface for estimating noise components using non-overlapping 2D convolutions over input image(s).

Parameters:

Name	Type	Description	Default
`module` ¶	`Conv2d`	The 2D convolutional module to use. The estimator must have a stride equal to its kernel size (non-overlapping) and output channels equal to the input channels times the product of the kernel side lengths (input volume = output volume).	required
`target_parameter` ¶	`str`	The name of the parameter to pass the input tensor as to the `module`.	`'input'`
`parameterization` ¶	`OptionalParameterizationT`	The optional parameterization to apply to the output of the estimator.	`None`
`masker` ¶	`OptionalMaskerT`	The optional masker to apply to the output of the parameterization.	`None`
`padding_mode` ¶	`Literal['constant', 'reflect', 'replicate', 'circular']`	Type of padding. One of: constant, reflect, replicate, or circular.	`'constant'`
`padding_value` ¶	`float`	Fill value for constant padding.	`0.0`

Raises:

Type	Description
`ValueError`	If the stride is not equal to the kernel size.
`ValueError`	If the output channels are not equal to the input channels times the product of the kernel side lengths.
`ValueError`	If a non-zero padding value is given for a padding mode other than constant.

Added in version 0.40.0.

Methods:

Name	Description
`__call__`	Estimate noise components from input values.
`forward`	Estimate noise components from input values.
`module_from_input_shape`	Construct a non-overlapping Conv2d from the given parameters.
`reset_parameters`	Reinitialize parameters and buffers.

call ¶

__call__(
    input: Tensor,
    noise_mask: Tensor | None = None,
    **kwargs: Any,
) -> tuple[torch.Tensor, torch.Tensor | None]

__call__(
    input: Tensor,
    noise_mask: Tensor | None = None,
    **kwargs: Any,
) -> tuple[torch.Tensor, torch.Tensor | None]

__call__(
    input: Tensor,
    noise_mask: Tensor | None = None,
    **kwargs: Any,
) -> tuple[torch.Tensor, torch.Tensor | None]

__call__(
    input: Tensor,
    noise_mask: Tensor | None = None,
    **kwargs: Any,
) -> tuple[torch.Tensor, torch.Tensor | None]

Estimate noise components from input values.

Parameters:

Name	Type	Description	Default
`input` ¶	`Tensor`	The tensor to estimate noise components from.	required
`noise_mask` ¶	`Tensor \| None`	An optional mask tensor to use to select a subset of the elements of the estimated standard deviations for computing a mask to apply to the input. If `None`, the mask is computed over all of the estimated standard deviations.	`None`
`kwargs` ¶	`Any`	Additional keyword arguments to `module`.	required

Returns:

Type	Description
`tuple[torch.Tensor, torch.Tensor \| None]`	A tuple containing the estimated noise components and an input mask if there is a `masker`.

forward ¶

forward(
    input: Tensor,
    noise_mask: Tensor | None = None,
    **kwargs: Any,
) -> tuple[torch.Tensor, torch.Tensor | None]

Estimate noise components from input values.

Parameters:

Name	Type	Description	Default
`input` ¶	`Tensor`	The tensor to estimate noise components from.	required
`noise_mask` ¶	`Tensor \| None`	An optional mask tensor to use to select a subset of the elements of the estimated standard deviations for computing a mask to apply to the input. If `None`, the mask is computed over all of the estimated standard deviations.	`None`
`kwargs` ¶	`Any`	Additional keyword arguments to `module`.	required

Returns:

Type	Description
`tuple[torch.Tensor, torch.Tensor \| None]`	A tuple containing the estimated noise components and an input mask if there is a `masker`.

module_from_input_shape `staticmethod` ¶

module_from_input_shape(
    color_channels: int,
    patch_size: int | tuple[int, int] | Sequence[int],
) -> nn.Conv2d

Construct a non-overlapping Conv2d from the given parameters.

Parameters:

Name	Type	Description	Default
`color_channels` ¶	`int`	The number of color channels in the input image(s).	required
`patch_size` ¶	`int \| tuple[int, int] \| Sequence[int]`	The dimension of the non-overlapping rectangular patches to tile the image with; if a single value is given, a square patch will be used.	required

Returns:

Type	Description
`nn.Conv2d`	The constructed Conv2d.

reset_parameters ¶

reset_parameters() -> None

Reinitialize parameters and buffers.

This method is useful for initializing tensors created on the meta device.

estimators

Estimator ¶

`module` ¶

`target_parameter` ¶

`parameterization` ¶

`masker` ¶

call ¶

`input` ¶

`noise_mask` ¶

`kwargs` ¶

forward ¶

`input` ¶

`noise_mask` ¶

`kwargs` ¶

reset_parameters ¶

PatchEstimator ¶

`module` ¶

`target_parameter` ¶

`parameterization` ¶

`masker` ¶

`padding_mode` ¶

`padding_value` ¶

call ¶

`input` ¶

`noise_mask` ¶

`kwargs` ¶

forward ¶

`input` ¶

`noise_mask` ¶

`kwargs` ¶

module_from_input_shape `staticmethod` ¶

`color_channels` ¶

`patch_size` ¶

reset_parameters ¶

estimators

Estimator ¶

module ¶

target_parameter ¶

parameterization ¶

masker ¶

__call__ ¶

input ¶

noise_mask ¶

kwargs ¶

forward ¶

input ¶

noise_mask ¶

kwargs ¶

reset_parameters ¶

PatchEstimator ¶

module ¶

target_parameter ¶

parameterization ¶

masker ¶

padding_mode ¶

padding_value ¶

__call__ ¶

input ¶

noise_mask ¶

kwargs ¶

forward ¶

input ¶

noise_mask ¶

kwargs ¶

module_from_input_shape staticmethod ¶

color_channels ¶

patch_size ¶

reset_parameters ¶

`module` ¶

`target_parameter` ¶

`parameterization` ¶

`masker` ¶

call ¶

`input` ¶

`noise_mask` ¶

`kwargs` ¶

`input` ¶

`noise_mask` ¶

`kwargs` ¶

`module` ¶

`target_parameter` ¶

`parameterization` ¶

`masker` ¶

`padding_mode` ¶

`padding_value` ¶

call ¶

`input` ¶

`noise_mask` ¶

`kwargs` ¶

`input` ¶

`noise_mask` ¶

`kwargs` ¶

module_from_input_shape `staticmethod` ¶

`color_channels` ¶

`patch_size` ¶