mapping_networks.losses.MappingLoss

class mapping_networks.losses.MappingLoss(task_loss: BaseLoss, stability_loss: BaseLoss | None = None, smoothness_loss: BaseLoss | None = None, alignment_loss: BaseLoss | None = None, lambda_stability: float = 0.1, lambda_smoothness: float = 0.01, lambda_alignment: float = 0.01, *, trainable_coefficients: bool = False)

Composite loss implementing the paper’s multi-component mapping loss.

Combines a required task loss with optional stability, smoothness, and alignment components. Each optional component is weighted by a corresponding lambda coefficient.

When trainable_coefficients=True, lambdas are stored as raw nn.Parameter values and passed through softplus at compute time to guarantee non-negativity. This matches the paper’s description of trainable regularization coefficients.

When trainable_coefficients=False (default), lambdas are plain floats and are not included in the model’s parameter groups.

Parameters:

• task_loss – Required task loss component.

• stability_loss – Optional stability loss. Set to None to disable.

• smoothness_loss – Optional smoothness loss. Set to None to disable.

• alignment_loss – Optional alignment loss. Set to None to disable.

• lambda_stability – Weight for the stability component.

• lambda_smoothness – Weight for the smoothness component.

• lambda_alignment – Weight for the alignment component.

• trainable_coefficients – If True, lambda values become trainable parameters (passed through softplus for non-negativity).

Example:

loss_fn = MappingLoss(
    task_loss=ClassificationLoss(),
    stability_loss=StabilityLoss(epsilon=0.01),
    smoothness_loss=SmoothnessLoss(method="stochastic"),
    lambda_stability=0.1,
    lambda_smoothness=0.01,
    trainable_coefficients=False,
)
output = loss_fn(context)
output.total.backward()

__init__(task_loss: BaseLoss, stability_loss: BaseLoss | None = None, smoothness_loss: BaseLoss | None = None, alignment_loss: BaseLoss | None = None, lambda_stability: float = 0.1, lambda_smoothness: float = 0.01, lambda_alignment: float = 0.01, *, trainable_coefficients: bool = False) → None

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

Methods

__init__(task_loss[, stability_loss, ...])	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.
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(context)	Compute the composite loss and return structured output.
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([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.
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.
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
lambda_alignment
lambda_smoothness
lambda_stability
training