vraven · function
explain
explain(model: 'Any', inputs: 'Any', target: 'int | Sequence[int] | torch.Tensor | None' = None, *, mode: 'str' = 'fast', config: 'VRavenConfig | None' = None, class_names: 'Mapping[int, str] | Sequence[str] | None' = None, metadata: 'dict[str, Any] | None' = None, **config_overrides: 'Any') -> 'VRavenReport'Explain one model invocation using the simple functional API.
Usage
import vraven
report = vraven.explain(model=model, inputs=x, target=target, mode="causal")
report.write_report("explanation.html")
Source of truthThis page is generated from the checked-out public symbol, signature, and docstring. Pin the package version for reproducible work.