Collected sources and patterns will appear here. Add from search, explore, or the patterns library.
InferenceEngine, InputTensor, NodeName -> OutputTensor
Resolve dynamic tensor references and perform multi-branch inference by extracting data directly from a designated node name in the engine graph.
Problem it solves
Standard sequential execution models prevent inspecting intermediate layer tensors or executing sub-branches dynamically.
Consumes
Emits
The real projects this mechanism was found in. Attribution is the point — this is how the best teams actually do it.