incerto.ood.MaxLogit

class incerto.ood.MaxLogit(model)

Bases: OODDetector

MaxLogit OOD detection (Hendrycks et al., 2019).

Uses the maximum logit value as the OOD score. Simpler than MSP and often more effective as it doesn’t require softmax normalization.

__init__(model)

Initialize the OOD detector with a trained model.

The model is automatically: 1. Set to eval mode 2. Has gradients disabled (requires_grad=False)

Parameters:

model – A trained PyTorch model (nn.Module)

Methods

__init__(model)	Initialize the OOD detector with a trained model.
load_state_dict(state)	Load detector state from a dictionary.
predict(x, threshold)	Predict whether inputs are OOD using a threshold.
save(path)	Save detector state to a file (excluding the model).
score(x)	Compute OOD scores for input samples.
state_dict()	Return a dictionary containing the detector's state.

score(x)

Compute OOD scores for input samples.

Higher scores indicate the input is more likely to be out-of-distribution.

Parameters:

x – Input tensor of shape (batch_size, *input_dims)

Returns:

OOD scores of shape (batch_size,) where higher values indicate more OOD-like samples.

Note

The scale of scores depends on the detection method. Use the predict() method with a threshold for binary OOD decisions.