vraven.decompiler · class
VRavenDecompiler
VRavenDecompiler(config: 'DecompileConfig | None' = None) -> 'None'Recover a tested high-level mechanism from a previously unseen PyTorch model.
Usage
from vraven.decompiler import VRavenDecompiler
value = VRavenDecompiler(...)Methods
reverse(self, model: 'nn.Module', reference_args: 'Sequence[Any]', *, reference_kwargs: 'Mapping[str, Any] | None' = None, labels: 'Sequence[int] | np.ndarray | Tensor | None' = None, sample_ids: 'Sequence[str] | None' = None, focus_args: 'Sequence[Any] | None' = None, focus_kwargs: 'Mapping[str, Any] | None' = None, target: 'int | None' = None, class_names: 'Mapping[int, str] | Sequence[str] | None' = None, input_groups: 'Mapping[str, Sequence[int]] | None' = None, validated_input_groups: 'Sequence[str] | None' = None, domain_validator: 'DomainValidator | None' = None) -> 'DecompilationResult'
Public method.
Source of truthThis page is generated from the checked-out public symbol, signature, and docstring. Pin the package version for reproducible work.