avalanche.models.FeCAMClassifier

class avalanche.models.FeCAMClassifier(tukey=True, shrinkage=True, shrink1: float = 1.0, shrink2: float = 1.0, tukey1: float = 0.5, covnorm=True)

Similar to NCM but uses malahanobis distance instead of l2 distance

This approach has been proposed for continual learning in “FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning” Goswami et. al. (Neurips 2023)

This requires the storage of full per-class covariance matrices

__init__(tukey=True, shrinkage=True, shrink1: float = 1.0, shrink2: float = 1.0, tukey1: float = 0.5, covnorm=True)

Parameters:

• tukey –

  whether to use the tukey transforms (help get the distribution closer

  to multivariate gaussian)

• shrinkage – whether to shrink the covariance matrices

• shrink1 –

• shrink2 –

• tukey1 – power in tukey transforms

• covnorm – whether to normalize the covariance matrix

Methods

__init__([tukey, shrinkage, shrink1, ...])	param tukey: whether to use the tukey transforms
adaptation(experience)	Adapt the module (freeze units, add units...) using the current data.
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.
apply_cov_transforms(class_cov)
apply_invert_transforms(features)
apply_transforms(features)
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)	param x: (batch_size, feature_size)
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.
init_missing_classes(classes, class_size, device)
ipu([device])	Move all model parameters and buffers to the IPU.
load_state_dict(state_dict[, strict])	Copy parameters and buffers from state_dict into this module and its descendants.
modules()	Return an iterator over all modules in the network.
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.
pre_adapt(agent, experience)	Calls self.adaptation recursively accross the hierarchy of pytorch module childrens
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_module(name, module)	Alias for add_module().
register_parameter(name, param)	Add a parameter to the module.
register_state_dict_pre_hook(hook)	Register a pre-hook for the state_dict() method.
replace_class_cov_dict(class_cov_dict)
replace_class_means_dict(class_means_dict)
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.
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_class_cov_dict(class_cov_dict[, momentum])
update_class_means_dict(class_means_dict[, ...])
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