ARTICLE AD BOX
I’m migrating my Android project from the bundled TensorFlow Lite to TensorFlow Lite via Google Play Services (LiteRT).
I use Movinet, which uses signatures and I’m feeding it individual video frames one by one for streaming inference.
In the old bundled Interpreter class, I could use:
interpreter.runSignature(inputs, outputs, "serving_default")
However, after migrating to InterpreterApi from Play Services, this method does not appear to be available — InterpreterApi only exposes run() and runForMultipleInputsOutputs().
How to use TFLite model signatures with InterpreterApi?
