incerto.bayesian.DeepEnsemble

class incerto.bayesian.DeepEnsemble(model_fn, num_models=5)

Bases: Module

Deep Ensembles for uncertainty quantification.

Trains multiple neural networks independently and aggregates their predictions. This is one of the most effective methods for uncertainty estimation in deep learning.

Reference:

Lakshminarayanan et al., “Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles” (NeurIPS 2017)

Parameters:

• model_fn (Callable[[], Module]) – Function that creates a new model instance

• num_models (int) – Number of ensemble members (default: 5)

Example

>>> def create_model():
...     return ResNet18(num_classes=10)
>>> ensemble = DeepEnsemble(create_model, num_models=5)
>>> # Train each model separately
>>> for i in range(5):
...     train_model(ensemble.models[i], train_loader)
>>> mean, variance = ensemble.predict(x)

__init__(model_fn, num_models=5)

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

Parameters:

• model_fn (Callable[[], Module])

• num_models (int)

Methods

__init__(model_fn[, num_models])	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.
diversity(x)	Compute ensemble diversity (disagreement).
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(x[, model_idx])	Forward pass through a specific model or all models.
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()	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.
predict(x[, return_all])	Ensemble prediction with uncertainty.
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.
train_member(model_idx, train_loader, ...[, ...])	Train a specific ensemble member.
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
training

__init__(model_fn, num_models=5)

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

Parameters:

• model_fn (Callable[[], Module])

• num_models (int)

forward(x, model_idx=None)

Forward pass through a specific model or all models.

Parameters:

• x (Tensor) – Input tensor

• model_idx (Optional[int]) – If specified, use only this model. Otherwise average all.

Return type:

Tensor

Returns:

Model output(s)

predict(x, return_all=False)

Ensemble prediction with uncertainty.

Parameters:

• x (Tensor) – Input tensor (N, *)

• return_all (bool) – If True, return all individual predictions

Return type:

Tuple[Tensor, Tensor]

Returns:

Tuple of (mean_prediction, predictive_variance) If return_all=True: (mean, variance, all_predictions)

train_member(model_idx, train_loader, optimizer, criterion, num_epochs=10, device='cuda')

Train a specific ensemble member.

Parameters:

• model_idx (int) – Index of model to train

• train_loader (DataLoader) – Training data loader

• optimizer (Optimizer) – Optimizer instance

• criterion (Module) – Loss function

• num_epochs (int) – Number of training epochs

• device (str) – Device to train on

diversity(x)

Compute ensemble diversity (disagreement).

Parameters:

x (Tensor) – Input tensor

Return type:

Tensor

Returns:

Per-sample diversity score