mixmo.core.loss.WrapperLoss

class mixmo.core.loss.WrapperLoss(config_loss, config_args, device)

Bases: mixmo.core.loss.AbstractLoss

Wrapper around the multiple losses. Initialized from listloss.

__init__(config_loss, config_args, device)

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

Methods

__init__(config_loss, config_args, device)	Initializes internal Module state, shared by both nn.Module and ScriptModule.
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.
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.
extra_repr()	Set the extra representation of the module
float()	Casts all floating point parameters and buffers to float datatype.
forward(input, target)	Defines the computation performed at every call.
get_accumulator_stats([format, split])	Gather tracked stats into a dictionary as formatted strings
half()	Casts all floating point parameters and buffers to half datatype.
l2_reg()	Compute l2 regularization/weight decay over the non-excluded parameters
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])	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.
print_details()
register_backward_hook(hook)	Registers a backward hook on the module.
register_buffer(name, tensor)	Adds a persistent 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_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_regularized_network(network)
share_memory()
start_accumulator()
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.
train([mode])	Sets the module in training mode.
type(dst_type)	Casts all parameters and buffers to dst_type.
zero_grad()	Sets gradients of all model parameters to zero.

Attributes

dump_patches

This allows better BC support for load_state_dict().

_forward(input, target)

Perform loss forwards for each sublosses and l2 reg

_forward_subloss(loss, input, target)

Standard loss forward for one of the sublosses

_init_get_losses()

Initialize and gather losses from listloss

get_accumulator_stats(format='short', split=None)

Gather tracked stats into a dictionary as formatted strings

l2_reg()

Compute l2 regularization/weight decay over the non-excluded parameters