ConformalClsRAPS#

class torch_uncertainty.post_processing.ConformalClsRAPS(alpha, model=None, randomized=True, penalty=0.1, regularization_rank=1, ts_init_val=1.0, ts_lr=0.1, ts_max_iter=100, enable_ts=False, device=None)[source]#

Conformal prediction with RAPS scores.

Parameters:

  • alpha (float) – The confidence level meaning we allow \(1-\alpha\) error.

  • model (nn.Module) – Trained classification model. Defaults to None.

  • randomized (bool) – Whether to use randomized smoothing in RAPS. Defaults to True.

  • penalty (float) – Regularization weight. Defaults to 0.1.

  • regularization_rank (int) – Rank threshold for regularization. Defaults to 1.

  • ts_init_val (float, optional) – Initial value for the temperature. Defaults to 1.0.

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

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

  • enable_ts (bool) – Whether to scale the logits. Defaults to False.

  • device (Literal["cpu", "cuda"] | torch.device | None, optional) – device. Defaults to None.

Reference:

  • TODO:

Code inspired by TorchCP.

conformal(inputs)#

Compute the prediction set for each input.

fit(dataloader)#

Calibrate the APS threshold q_hat on a calibration set.

model_forward(inputs)#

Apply the model and return the scores.