avalanche.models.MultiHeadClassifier

class avalanche.models.MultiHeadClassifier(in_features, initial_out_features=2, masking=True, mask_value=- 1000)[source]

Multi-head classifier with separate heads for each task.

Typically used in task-incremental benchmarks where task labels are available and provided to the model.

Note

Each output head may have a different shape, and the number of classes can be determined automatically.

However, since pytorch doest not support jagged tensors, when you compute a minibatch’s output you must ensure that each sample has the same output size, otherwise the model will fail to concatenate the samples together.

These can be easily ensured in two possible ways:

  • each minibatch contains a single task, which is the case in most

    common benchmarks in Avalanche. Some exceptions to this setting are multi-task replay or cumulative strategies.

  • each head has the same size, which can be enforced by setting a

    large enough initial_out_features.

__init__(in_features, initial_out_features=2, masking=True, mask_value=- 1000)[source]

Init.

Parameters
  • in_features – number of input features.

  • initial_out_features – initial number of classes (can be dynamically expanded).

  • masking – whether unused units should be masked (default=True).

  • mask_value – the value used for masked units (default=-1000).

Methods

__init__(in_features[, ...])

Init.

adaptation(experience)

If dataset contains new tasks, a new head is initialized.

add_module(name, module)

Adds a child module to the current module.

apply(fn)

Applies 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])

Returns an iterator over module buffers.

children()

Returns an iterator over immediate children modules.

cpu()

Moves all model parameters and buffers to the CPU.

cuda([device])

Moves all model parameters and buffers to the GPU.

double()

Casts all floating point parameters and buffers to double datatype.

eval()

Sets the module in evaluation mode.

eval_adaptation(experience)

Module's adaptation at evaluation time.

extra_repr()

Set the extra representation of the module

float()

Casts all floating point parameters and buffers to float datatype.

forward(x, task_labels)

compute the output given the input x and task labels.

forward_all_tasks(x)

compute the output given the input x and task label.

forward_single_task(x, task_label)

compute the output given the input x.

get_buffer(target)

Returns the buffer given by target if it exists, otherwise throws an error.

get_extra_state()

Returns any extra state to include in the module's state_dict.

get_parameter(target)

Returns the parameter given by target if it exists, otherwise throws an error.

get_submodule(target)

Returns the submodule given by target if it exists, otherwise throws an error.

half()

Casts all floating point parameters and buffers to half datatype.

load_state_dict(state_dict[, strict])

Copies parameters and buffers from state_dict into this module and its descendants.

modules()

Returns an iterator over all modules in the network.

named_buffers([prefix, recurse])

Returns an iterator over module buffers, yielding both the name of the buffer as well as the buffer itself.

named_children()

Returns 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])

Returns 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])

Returns an iterator over module parameters, yielding both the name of the parameter as well as the parameter itself.

parameters([recurse])

Returns an iterator over module parameters.

register_backward_hook(hook)

Registers a backward hook on the module.

register_buffer(name, tensor[, persistent])

Adds a buffer to the module.

register_forward_hook(hook)

Registers a forward hook on the module.

register_forward_pre_hook(hook)

Registers a forward pre-hook on the module.

register_full_backward_hook(hook)

Registers a backward hook on the module.

register_module(name, module)

Alias for add_module().

register_parameter(name, param)

Adds a parameter to the module.

requires_grad_([requires_grad])

Change if autograd should record operations on parameters in this module.

set_extra_state(state)

This function is called from load_state_dict() to handle any extra state found within the state_dict.

share_memory()

See torch.Tensor.share_memory_()

state_dict([destination, prefix, keep_vars])

Returns a dictionary containing a whole state of the module.

to(*args, **kwargs)

Moves and/or casts the parameters and buffers.

to_empty(*, device)

Moves the parameters and buffers to the specified device without copying storage.

train([mode])

Sets the module in training mode.

train_adaptation([experience])

Update known task labels.

type(dst_type)

Casts all parameters and buffers to dst_type.

xpu([device])

Moves all model parameters and buffers to the XPU.

zero_grad([set_to_none])

Sets gradients of all model parameters to zero.

Attributes

T_destination

alias of TypeVar('T_destination', bound=Mapping[str, Tensor])

dump_patches

This allows better BC support for load_state_dict().