incerto.calibration.TemperatureScaling

class incerto.calibration.TemperatureScaling(init_temp=1.0)

Bases: Module, BaseCalibrator

Temperature scaling for post-hoc probabilistic calibration.

Learns a single positive scalar temperature T that rescales logits as z / T before softmax. The temperature is fit by minimizing NLL on a held-out validation set using L-BFGS. Predictions remain argmax-preserving, so accuracy is unchanged.

Reference:

Guo et al., “On Calibration of Modern Neural Networks”, ICML 2017.

Parameters:

init_temp (float) – Initial temperature value. Must be > 0. Default: 1.0.

Example

>>> calibrator = TemperatureScaling()
>>> calibrator.fit(val_logits, val_labels)
>>> calibrated = calibrator.predict(test_logits)  # Categorical distribution

__init__(init_temp=1.0)

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

Parameters:

init_temp (float)

Methods

__init__([init_temp])	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.
fit(logits, labels[, lr, max_iters])	Fit temperature by minimizing NLL on validation logits and labels.
float()	Casts all floating point parameters and buffers to float datatype.
forward(logits)	Apply temperature scaling to logits.
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(path)	Load a calibrator from a file.
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.
predict(logits)	Return a calibrated categorical distribution over classes.
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.
save(path)	Save calibrator state to a file.
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
training

fit(logits, labels, lr=0.01, max_iters=50)

Fit temperature by minimizing NLL on validation logits and labels.

Parameters:

• logits (Tensor) – Tensor of shape (n_samples, n_classes).

• labels (Tensor) – Tensor of shape (n_samples,) with integer class indices in [0, n_classes).

• lr (float) – Learning rate for the L-BFGS optimizer.

• max_iters (int) – Maximum iterations for the optimizer.

Returns:

self

forward(logits)

Apply temperature scaling to logits.

Parameters:

logits (Tensor) – Tensor of shape (n_samples, n_classes).

Return type:

Tensor

Returns:

Scaled logits of the same shape.

predict(logits)

Return a calibrated categorical distribution over classes.

Parameters:

logits (Tensor) – Tensor of shape (n_samples, n_classes).

Return type:

Categorical

Returns:

A torch.distributions.Categorical whose probs attribute holds the calibrated probabilities of shape (n_samples, n_classes).