MatrixScaler#

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

Matrix scaling post-processing for calibrated probabilities.

Parameters:

  • num_classes (int) – Number of classes.

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

  • init_weight_temperature (float | Tensor , optional) – Initial value for the weights. Defaults to 1.

  • init_bias_temperature (float | Tensor | None, optional) – Initial value for the bias. The inverse bias will be set to the 0 vector if set to None. Defaults to None.

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

  • max_iter (int, optional) – Maximum number of iterations for the optimizer. Defaults to 100.

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

  • device (Optional[Literal["cpu", "cuda"]], optional) – Device to use for optimization. Defaults to None.

References

[1] On calibration of modern neural networks. In ICML 2017.

Warning

If the model is binary, we will by default apply the sigmoid before transposing the prediction 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, optional) – Whether to save the logits and labels in memory. Defaults to False.

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

Warning

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

set_temperature(val_weight, val_bias)[source]#

Set the temperature matrix to a given value.

Parameters:

  • val_weight (float | Tensor) – Weight temperature value.

  • val_bias (float | Tensor) – Bias temperature value.