pydpf.distributions.base.Distribution

class pydpf.distributions.base.Distribution(generator: Generator, *args, **kwargs)

Bases: Module

Base class for implementations of common distributions. This is to provide a convenient API, similar to torch.distribution. If a user wants to create a custom distribution it will almost always be easier to subclass Module and manually implement sample and log_density methods rather than to subclass Distribution.

Distribution samples have the following dimension order: Batch X Samples X Data

Data is always a single dimension and is inferred from the distribution parameters, which must not be batched.

Batch can be any number of batch dimensions, it is inferred from the conditioning variables. For unconditional distributions the batch size is always 0.

Samples can be any number of dimensions, it is manually supplied when calling Distribution.sample(). When calling Distribution.log_density() it is inferred as the dimensions of the supplied sample that aren’t Batch or Data.

Log_density returns the log density of each datum in a sample in a batch. Rather than reducing over the sample.

__init__(generator: Generator, *args, **kwargs) → None

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

Methods

__init__(generator, *args, **kwargs)	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.
check_sample(sample)	Check that the sample matches the defined dimension of the distribution.
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(*args, **kwargs)	Do not implement a forward method for a Distribution
get_batch_size(size, data_dims)	Get the size of a tensor excluding the last (data_size) dimensions.
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.
log_density(*args, **kwargs)
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.
sample(*args, **kwargs)
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
conditional
dump_patches
training

check_sample(sample)

Check that the sample matches the defined dimension of the distribution.

conditional = False

forward(*args, **kwargs) → None

Do not implement a forward method for a Distribution

static get_batch_size(size: Tuple[int, ...], data_dims: int) → Tuple[int, ...]

Get the size of a tensor excluding the last (data_size) dimensions.

Parameters:

sizeTuple[int}

The size to extract the batch dimensions from.

data_dimsint

The number of non-batch dimensions to extract.

Returns:

batch_sizeTuple[int]

The extracted batch dimensions.

abstractmethod log_density(*args, **kwargs) → Tensor

abstractmethod sample(*args, **kwargs) → Tensor