tfep.nn.flows.autoregressive.AutoregressiveFlow

class tfep.nn.flows.autoregressive.AutoregressiveFlow(n_features_in: int, transformer_indices: Sequence[Sequence[int]], conditioner: Module, transformer: Module, conditioner_indices: Sequence[int] | None = None, initialize_identity: bool = True)

Bases: Module

Autoregressive flow.

This implements a generic autoregressive flow based on the framework described in [1] in which the features are transformed by a transformer parametrized by a conditioner layer.

See also

Conditioner

Documents the API of a conditioner layer.

Transformer

Documents the API of a transformer.

References

[1] Papamakarios G, Pavlakou T, Murray I. Masked autoregressive flow for

density estimation. In Advances in Neural Information Processing Systems 2017 (pp. 2338-2347).

__init__(n_features_in: int, transformer_indices: Sequence[Sequence[int]], conditioner: Module, transformer: Module, conditioner_indices: Sequence[int] | None = None, initialize_identity: bool = True)

Constructor.

Parameters:

• n_features_in (int, optional) – Total number of input features.

• transformer_indices (Sequence[Sequence[int]]) – The feature indices (possibly a subset of the input features) passed to the transformer grouped by their order in the autoregressive model. This information is required to evaluate the inverse which generally requires multiple passes (see ref. [1]). Any feature not in this sequence is considered fixed and propagated without changes by the flow.

  For example, [[0, 2], [3], [1, 4] specifies an autoregressive model in which the features 0,2 do not depend on any other transformed feature (although it might depend on other fixed features entering the conditioner), 3 depends on 0,2, and 1,4 depend on 0,2,3.

• conditioner (Conditioner) – The conditioner layer generating parameters for the transformer.

• transformer (Transformer) – The transformer used to map the input features.

• conditioner_indices (Sequence[int], optional) – The subset of features can be passed to the conditioner. By default, all input features are passed.

• initialize_identity (bool, optional) – If True, the flow is initialized to perform the identity function.

Methods

__init__(n_features_in, transformer_indices, ...)	Constructor.
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()	Set the extra representation of the module.
float()	Casts all floating point parameters and buffers to float datatype.
forward(x)	Push forward.
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.
get_transformer_parameters(x)	Compute the parameters for the transformer.
half()	Casts all floating point parameters and buffers to half datatype.
inverse(y)	Inverse.
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()	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)	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.
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
has_fixed_indices	True if some of the features are not transformed by the flow.
training

forward(x: Tensor) → Tensor

Push forward.

Parameters:

x (torch.Tensor) – Shape (batch_size, n_features). Input tensor.

Returns:

• y (torch.Tensor) – Shape (batch_size, n_features). Mapped features.

• log_det_J (torch.Tensor) – Shape (batch_size,). The log absolute value of the Jacobian of the transformation.

get_transformer_parameters(x: Tensor) → Tensor

Compute the parameters for the transformer.

Parameters:

x (torch.Tensor) – Shape (batch_size, n_features). The input tensor.

Returns:

Parameters – Shape (batch_size, n_parameters). The transformer parameters.

Return type:

torch.Tensor

property has_fixed_indices

True if some of the features are not transformed by the flow.

Type:

bool

inverse(y: Tensor) → Tensor

Inverse.

This is in general slower than the forward pass as it may require multiple passes (see ref. [1] for the algorithm).

Parameters:

y (torch.Tensor) – Shape (batch_size, n_features). Input tensor.

Returns:

• x (torch.Tensor) – Shape (batch_size, n_features). Mapped features.

• log_det_J (torch.Tensor) – Shape (batch_size,). The log absolute value of the Jacobian of the transformation.