torchsar.module.autofocus package

Submodules

torchsar.module.autofocus.autofocus module

class torchsar.module.autofocus.autofocus.AutoFocusBarePhi(Na, Nr, Nb=None, pa=None, pr=None, Ma=None, Mr=None, xa=None, xr=None, ftshift=False, trainable=True)

Bases: torch.nn.modules.module.Module

forward(X, isfft=True)

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

get_param()
param_init(pa=None, pr=None)
training: bool
class torchsar.module.autofocus.autofocus.AutoFocusDctPhi(Na, Nr, Nb=None, ca=None, cr=None, Pa=4, Pr=4, ftshift=False, trainable=True)

Bases: torch.nn.modules.module.Module

forward(X, isfft=True)

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

get_param()
param_init(ca=None, cr=None)
training: bool
class torchsar.module.autofocus.autofocus.AutoFocusPolyPhi(Na, Nr, Nb=None, ca=None, cr=None, Ma=2, Mr=2, xa=None, xr=None, ftshift=False, trainable=True)

Bases: torch.nn.modules.module.Module

forward(X, isfft=True)

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

get_param()
param_init(ca=None, cr=None)
training: bool
class torchsar.module.autofocus.autofocus.AutoFocusSinPhi(Na, Nr, Nb=None, aa=None, fa=None, ar=None, fr=None, ftshift=False, trainable=True)

Bases: torch.nn.modules.module.Module

forward(X, isfft=True)

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

get_param()
param_init(aa=None, fa=None, ar=None, fr=None)
training: bool

torchsar.module.autofocus.fast_fourier_domain_optimization module

class torchsar.module.autofocus.fast_fourier_domain_optimization.AutoFocusFFO(Na, Nr, Nb=None, ftshift=False, trainable=True)

Bases: torch.nn.modules.module.Module

forward(X, isfft=True)

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

get_param()
imaging(Xc)
param_init(pa=None, pr=None)
training: bool

torchsar.module.autofocus.focusing module

class torchsar.module.autofocus.focusing.AutoFocus(Na, Nr, pa=None, pr=None, ftshift=False, trainable=True)

Bases: torch.nn.modules.module.Module

forward(X, isfft=True)

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

training: bool

torchsar.module.autofocus.phase_error_model module

class torchsar.module.autofocus.phase_error_model.BarePhi(Na, Nr, Nb=None, pa=None, pr=None, Ma=None, Mr=None, xa=None, xr=None, shift=False, trainable=True)

Bases: torch.nn.modules.module.Module

forward()

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

get_param()
param_init(pa=None, pr=None)
training: bool
class torchsar.module.autofocus.phase_error_model.DctPhi(Na, Nr, Nb=None, ca=None, cr=None, Pa=4, Pr=4, shift=False, trainable=True)

Bases: torch.nn.modules.module.Module

forward()

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

get_param()
param_init(ca=None, cr=None)
training: bool
class torchsar.module.autofocus.phase_error_model.PolyPhi(Na, Nr, Nb=None, ca=None, cr=None, Ma=2, Mr=2, xa=None, xr=None, shift=False, trainable=True)

Bases: torch.nn.modules.module.Module

forward()

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

get_param()
param_init(ca=None, cr=None)
training: bool
class torchsar.module.autofocus.phase_error_model.SinPhi(Na, Nr, Nb=None, aa=None, fa=None, ar=None, fr=None, shift=False, trainable=True)

Bases: torch.nn.modules.module.Module

forward()

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

get_param()
param_init(fa=None, aa=None, fr=None, ar=None)
training: bool

Module contents