pydpf.resampling.SoftResampler

class pydpf.resampling.SoftResampler(softness: float, base_resampler: Module, device: device)

Bases: Module

Soft resampler.

Module for perfoming soft-resampling, (P. Karkus, D. Hsu and W. S. Lee ‘Particle Filter Networks with Application to Visual Localization’ 2018).

Soft resampling allows gradients to be passed through resampling by inducing importance weights. This is done by instead drawing the resampled particle from an alternative distribution and re-weighting the samples. The chosen alternative distribution is a mixture of the target with probability a; and a uniform distribution over the particles, with probability 1-a.

The softness parameter, can be thought of as trading off between unbiased gradients (softness = 0) and efficient resampling (softness = 1). With softness > 0, the resampled index depends (randomly) on the previous weights. The contribution to the gradient from this dependence is ignored.

Parameters:

softness: float

The trade-off parameter between unbiased gradients (softness = 0) and efficient resampling (softness = 1).

base_resampler: Module

The base resampler to use.

device: torch.device.

The device that filtering is performed on

Notes

Proposed in [1]. Like many of the resamplers in PyDPF this resampler acts on top of another resampler, generally this should be either MultinomialResampler, SystematicResampler or OptimalTransportResampler. Stacking other resamplers should be done with great care and in the order: – Resamplers that modify gradient computation above Resamplers that modify the weights above Resamplers that modify the distribution for given weights) –. But it will nearly always be safer to define a new resampler with the desired behaviour than to stack exotic resamplers.

References

[1]

Karkus P, Hsu D, Lee WS (2018). “Particle filter networks with application to visual localization.” In Proc. Conf. Robot Learn., pp. 169–178. PMLR, Zurich, CH.

__init__(softness: float, base_resampler: Module, device: device)

Initialize internal Module state, shared by both nn.Module and ScriptModule.

Methods

__init__(softness, base_resampler, device)	Initialize internal Module state, shared by both nn.Module and ScriptModule.
add_module(name, module)	Add a child module to the current module.
apply(fn)	Apply fn recursively to every submodule (as returned by .children()) as well as self.
bfloat16()	Casts all floating point parameters and buffers to bfloat16 datatype.
buffers([recurse])	Return an iterator over module buffers.
children()	Return an iterator over immediate children modules.
compile(*args, **kwargs)	Compile this Module's forward using torch.compile().
cpu()	Move all model parameters and buffers to the CPU.
cuda([device])	Move all model parameters and buffers to the GPU.
double()	Casts all floating point parameters and buffers to double datatype.
eval()	Set the module in evaluation mode.
extra_repr()	Return the extra representation of the module.
float()	Casts all floating point parameters and buffers to float datatype.
forward(state, weight, **data)	Run the soft-resampler
get_buffer(target)	Return the buffer given by target if it exists, otherwise throw an error.
get_extra_state()	Return any extra state to include in the module's state_dict.
get_parameter(target)	Return the parameter given by target if it exists, otherwise throw an error.
get_submodule(target)	Return the submodule given by target if it exists, otherwise throw an error.
half()	Casts all floating point parameters and buffers to half datatype.
ipu([device])	Move all model parameters and buffers to the IPU.
load_state_dict(state_dict[, strict, assign])	Copy parameters and buffers from state_dict into this module and its descendants.
modules([remove_duplicate])	Return an iterator over all modules in the network.
mtia([device])	Move all model parameters and buffers to the MTIA.
named_buffers([prefix, recurse, ...])	Return an iterator over module buffers, yielding both the name of the buffer as well as the buffer itself.
named_children()	Return an iterator over immediate children modules, yielding both the name of the module as well as the module itself.
named_modules([memo, prefix, remove_duplicate])	Return an iterator over all modules in the network, yielding both the name of the module as well as the module itself.
named_parameters([prefix, recurse, ...])	Return an iterator over module parameters, yielding both the name of the parameter as well as the parameter itself.
parameters([recurse])	Return an iterator over module parameters.
register_backward_hook(hook)	Register a backward hook on the module.
register_buffer(name, tensor[, persistent])	Add a buffer to the module.
register_forward_hook(hook, *[, prepend, ...])	Register a forward hook on the module.
register_forward_pre_hook(hook, *[, ...])	Register a forward pre-hook on the module.
register_full_backward_hook(hook[, prepend])	Register a backward hook on the module.
register_full_backward_pre_hook(hook[, prepend])	Register a backward pre-hook on the module.
register_load_state_dict_post_hook(hook)	Register a post-hook to be run after module's load_state_dict() is called.
register_load_state_dict_pre_hook(hook)	Register a pre-hook to be run before module's load_state_dict() is called.
register_module(name, module)	Alias for add_module().
register_parameter(name, param)	Add a parameter to the module.
register_state_dict_post_hook(hook)	Register a post-hook for the state_dict() method.
register_state_dict_pre_hook(hook)	Register a pre-hook for the state_dict() method.
requires_grad_([requires_grad])	Change if autograd should record operations on parameters in this module.
set_extra_state(state)	Set extra state contained in the loaded state_dict.
set_submodule(target, module[, strict])	Set the submodule given by target if it exists, otherwise throw an error.
share_memory()	See torch.Tensor.share_memory_().
state_dict(*args[, destination, prefix, ...])	Return a dictionary containing references to the whole state of the module.
to(*args, **kwargs)	Move and/or cast the parameters and buffers.
to_empty(*, device[, recurse])	Move the parameters and buffers to the specified device without copying storage.
train([mode])	Set the module in training mode.
type(dst_type)	Casts all parameters and buffers to dst_type.
update()	Update all constrained_parameters and cached_properties belonging to this Module.
xpu([device])	Move all model parameters and buffers to the XPU.
zero_grad([set_to_none])	Reset gradients of all model parameters.

Attributes

T_destination
call_super_init
dump_patches
training

forward(state: Tensor, weight: Tensor, **data)

Run the soft-resampler