VectorScaler#

class torch_uncertainty.post_processing.VectorScaler(num_classes, model=None, init_temperature=1, lr=0.1, max_iter=200, eps=1e-08, device=None)[source]#

Vector scaling post-processing for calibrated probabilities.

Generalises temperature scaling by learning a per-class temperature vector \(\mathbf{T} \in \mathbb{R}^C_{>0}\):

\[\tilde{\mathbf{p}}(\mathbf{x}) = \mathrm{softmax}\!\left(\mathbf{z}(\mathbf{x}) \oslash \mathbf{T}\right),\]

where \(\oslash\) is element-wise division. The \(C\) temperatures are fit jointly by minimising the cross-entropy on a held-out calibration set.

Parameters:

  • num_classes (int) – Number of classes \(C\).

  • model (Module | None) – Model to calibrate.

  • init_temperature (float | Tensor) – Initial value for the per-class temperature. A scalar broadcasts to all classes. Defaults to 1.

  • lr (float) – Learning rate for the optimizer. Defaults to 0.1.

  • max_iter (int) – Maximum number of iterations for the optimizer. Defaults to 200.

  • eps (float) – Small value for stability. Defaults to 1e-8.

  • device (Union[Literal['cpu', 'cuda'], device, None]) – Device to use for optimization. Defaults to None.

References

[1] Guo, C., Pleiss, G., Sun, Y., & Weinberger, K. Q. (2017). On calibration of modern neural networks. ICML 2017.

Warning

For binary models, a sigmoid is applied before the prediction is transposed to the 2-class case.

fit(dataloader, save_logits=False, progress=True)#

Fit the temperature parameters to the calibration data.

Parameters:

  • dataloader (DataLoader) – Dataloader with the logits and target of the calibration data.

  • save_logits (bool) – Whether to save the logits and labels in memory. Defaults to False.

  • progress (bool) – Whether to show a progress bar. Defaults to True.

Return type:

None

Warning

Please provide logits and not probabilities/likelihoods within the dataloader, otherwise the Scaler might converge to negative temperatures.

set_model(model)#

Attach a model to the post-processing module.

Return type:

None

set_temperature(val)[source]#

Set the temperature vector to a given value.

Parameters:

val (float | Tensor) – Weight temperature vector, or float.

Return type:

None