Interpreter Methods

Update allocations for all tensors. This will redim dependent tensors using the input tensor dimensionality as given. This is relatively expensive. If you know that your sizes are not changing, you need not call this.

The dispose function that implements IDisposable interface

Release all the unmanaged memory associated with this interpreter

Destructor

Get a tensor data structure.

Invoke the interpreter (run the whole graph in dependency order).

Release the managed resources. This function will be called during the disposal of the current object. override ride this function if you need to call the Dispose() function on any managed IDisposable object created by the current object

Set the number of threads available to the interpreter.

Enable or disable the NN API (Android Neural Network API)