struct Options
Options for configuring the
Interpreter.
Class
Interpreter
A TensorFlow Lite interpreter that performs inference from a given model.
Declaration
final class InterpreterTopics
Structures
Initializers
init(modelPath: String, options: Options?, delegates: [Delegate]?) throws
Creates a new instance with the given values.
Instance Properties
let delegates: [Delegate]?
An
Array of Delegates for the Interpreter to use to perform graph operations.var inputTensorCount: Int
The total number of input
Tensors associated with the model.let options: Options?
The configuration options for the
Interpreter.var outputTensorCount: Int
The total number of output
Tensors associated with the model.Instance Methods
func allocateTensors() throws
Allocates memory for all input
Tensors based on their Tensor.Shapes.func copy(Data, toInputAt: Int) throws -> Tensor
Copies the given data to the input
Tensor at the given index.func input(at: Int) throws -> Tensor
Returns the input
Tensor at the given index.func invoke() throws
Invokes the interpreter to perform inference from the loaded graph.
func output(at: Int) throws -> Tensor
Returns the output
Tensor at the given index.func resizeInput(at: Int, to: Tensor.Shape) throws
Resizes the input
Tensor at the given index to the specified Tensor.Shape.