Interpreter (JavaCPP Presets for TensorFlow 1.12.0-1.4.4 API)

java.lang.Object
- org.tensorflow.lite.Interpreter

All Implemented Interfaces:: AutoCloseable

public final class Interpreter
extends Object
implements AutoCloseable

Driver class to drive model inference with TensorFlow Lite.

A Interpreter encapsulates a pre-trained TensorFlow Lite model, in which operations are executed for model inference.

For example, if a model takes only one input and returns only one output:


 try (Interpreter interpreter = new Interpreter(file_of_a_tensorflowlite_model)) {
   interpreter.run(input, output);
 }

If a model takes multiple inputs or outputs:


 Object[] inputs = {input0, input1, ...};
 Map<Integer, Object> map_of_indices_to_outputs = new HashMap<>();
 float[][][] ith_output = new float[3][2][4];
 map_of_indices_to_outputs.put(i, ith_output);
 try (Interpreter interpreter = new Interpreter(file_of_a_tensorflowlite_model)) {
   interpreter.runForMultipleInputsOutputs(inputs, map_of_indices_to_outputs);
 }

Orders of inputs and outputs are determined when converting TensorFlow model to TensorFlowLite model with Toco.

WARNING:Instances of a Interpreter is not thread-safe. A Interpreter owns resources that must be explicitly freed by invoking close()

Nested Class Summary

Nested Classes
Modifier and Type Class and Description

static class Interpreter.Options
An options class for controlling runtime interpreter behavior.

Nested Classes
Modifier and Type	Class and Description
`static class`	`Interpreter.Options` An options class for controlling runtime interpreter behavior.

Constructor Summary

Constructors
Constructor and Description
`Interpreter(@NonNull ByteBuffer byteBuffer)` Initializes a `Interpreter` with a `ByteBuffer` of a model file.
`Interpreter(@NonNull ByteBuffer byteBuffer, int numThreads)` Deprecated. Prefer using the `Interpreter(ByteBuffer,Options)` constructor. This method will be removed in a future release.
`Interpreter(@NonNull ByteBuffer byteBuffer, Interpreter.Options options)` Initializes a `Interpreter` with a `ByteBuffer` of a model file and a set of custom `#Options`.
`Interpreter(@NonNull File modelFile)` Initializes a `Interpreter`
`Interpreter(@NonNull File modelFile, int numThreads)` Deprecated. Prefer using the `Interpreter(File,Options)` constructor. This method will be removed in a future release.
`Interpreter(@NonNull File modelFile, Interpreter.Options options)` Initializes a `Interpreter` and specifies the number of threads used for inference.
`Interpreter(@NonNull MappedByteBuffer mappedByteBuffer)` Deprecated. Prefer using the `Interpreter(ByteBuffer,Options)` constructor. This method will be removed in a future release.

Method Summary

All Methods Instance Methods Concrete Methods Deprecated Methods
Modifier and Type	Method and Description
`void`	`close()` Release resources associated with the `Interpreter`.
`protected void`	`finalize()`
`int`	`getInputIndex(String opName)` Gets index of an input given the op name of the input.
`Tensor`	`getInputTensor(int inputIndex)` Gets the Tensor associated with the provdied input index.
`int`	`getInputTensorCount()` Gets the number of input tensors.
`Long`	`getLastNativeInferenceDurationNanoseconds()` Returns native inference timing.
`int`	`getOutputIndex(String opName)` Gets index of an output given the op name of the output.
`Tensor`	`getOutputTensor(int outputIndex)` Gets the Tensor associated with the provdied output index.
`int`	`getOutputTensorCount()` Gets the number of output Tensors.
`void`	`resizeInput(int idx, @NonNull int[] dims)` Resizes idx-th input of the native model to the given dims.
`void`	`run(@NonNull Object input, @NonNull Object output)` Runs model inference if the model takes only one input, and provides only one output.
`void`	`runForMultipleInputsOutputs(@NonNull Object[] inputs, @NonNull Map<Integer,Object> outputs)` Runs model inference if the model takes multiple inputs, or returns multiple outputs.
`void`	`setNumThreads(int numThreads)` Deprecated. Prefer using `Interpreter.Options.setNumThreads(int)` directly for controlling thread multi-threading. This method will be removed in a future release.
`void`	`setUseNNAPI(boolean useNNAPI)` Deprecated. Prefer using `Interpreter.Options.setUseNNAPI(boolean)` directly for enabling NN API. This method will be removed in a future release.

Methods inherited from class java.lang.Object
clone, equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

- Constructor Detail
  - Interpreter
```
public Interpreter(@NonNull File modelFile)
```
    Initializes a Interpreter
    
    Parameters:
    
    modelFile: - a File of a pre-trained TF Lite model.
  - Interpreter
```
@Deprecated
public Interpreter(@NonNull File modelFile,
                                int numThreads)
```
    Deprecated. Prefer using the Interpreter(File,Options) constructor. This method will be removed in a future release.
    
    Initializes a Interpreter and specifies the number of threads used for inference.
    
    Parameters:
    
    modelFile: - a file of a pre-trained TF Lite model
    
    numThreads: - number of threads to use for inference
  - Interpreter
```
public Interpreter(@NonNull File modelFile,
                   Interpreter.Options options)
```
    Initializes a Interpreter and specifies the number of threads used for inference.
    
    Parameters:
    
    modelFile: - a file of a pre-trained TF Lite model
    
    options: - a set of options for customizing interpreter behavior
  - Interpreter
```
public Interpreter(@NonNull ByteBuffer byteBuffer)
```
    Initializes a Interpreter with a ByteBuffer of a model file.
    The ByteBuffer should not be modified after the construction of a Interpreter. The ByteBuffer can be either a MappedByteBuffer that memory-maps a model file, or a direct ByteBuffer of nativeOrder() that contains the bytes content of a model.
  - Interpreter
```
@Deprecated
public Interpreter(@NonNull ByteBuffer byteBuffer,
                                int numThreads)
```
    Deprecated. Prefer using the Interpreter(ByteBuffer,Options) constructor. This method will be removed in a future release.
    
    Initializes a Interpreter with a ByteBuffer of a model file and specifies the number of threads used for inference.
    The ByteBuffer should not be modified after the construction of a Interpreter. The ByteBuffer can be either a MappedByteBuffer that memory-maps a model file, or a direct ByteBuffer of nativeOrder() that contains the bytes content of a model.
  - Interpreter
```
@Deprecated
public Interpreter(@NonNull MappedByteBuffer mappedByteBuffer)
```
    Deprecated. Prefer using the Interpreter(ByteBuffer,Options) constructor. This method will be removed in a future release.
    
    Initializes a Interpreter with a MappedByteBuffer to the model file.
    The MappedByteBuffer should remain unchanged after the construction of a Interpreter.
  - Interpreter
```
public Interpreter(@NonNull ByteBuffer byteBuffer,
                   Interpreter.Options options)
```
    Initializes a Interpreter with a ByteBuffer of a model file and a set of custom #Options.
    The ByteBuffer should not be modified after the construction of a Interpreter. The ByteBuffer can be either a MappedByteBuffer that memory-maps a model file, or a direct ByteBuffer of nativeOrder() that contains the bytes content of a model.
- Method Detail
  - run
```
public void run(@NonNull Object input,
                @NonNull Object output)
```
    Runs model inference if the model takes only one input, and provides only one output.
    Warning: The API runs much faster if ByteBuffer is used as input data type. Please consider using ByteBuffer to feed input data for better performance.
    
    Parameters:
    
    input - an array or multidimensional array, or a ByteBuffer of primitive types including int, float, long, and byte. ByteBuffer is the preferred way to pass large input data. When ByteBuffer is used, its content should remain unchanged until model inference is done.
    
    output - a multidimensional array of output data, or a ByteBuffer of primitive types including int, float, long, and byte.
  - runForMultipleInputsOutputs
```
public void runForMultipleInputsOutputs(@NonNull Object[] inputs,
                                        @NonNull Map<Integer,Object> outputs)
```
    Runs model inference if the model takes multiple inputs, or returns multiple outputs.
    Warning: The API runs much faster if ByteBuffer is used as input data type. Please consider using ByteBuffer to feed input data for better performance.
    
    Parameters:
    
    inputs - an array of input data. The inputs should be in the same order as inputs of the model. Each input can be an array or multidimensional array, or a ByteBuffer of primitive types including int, float, long, and byte. ByteBuffer is the preferred way to pass large input data. When ByteBuffer is used, its content should remain unchanged until model inference is done.
    
    outputs - a map mapping output indices to multidimensional arrays of output data or ByteBuffers of primitive types including int, float, long, and byte. It only needs to keep entries for the outputs to be used.
  - resizeInput
```
public void resizeInput(int idx,
                        @NonNull int[] dims)
```
    Resizes idx-th input of the native model to the given dims.
    IllegalArgumentException will be thrown if it fails to resize.
  - getInputTensorCount
```
public int getInputTensorCount()
```
    Gets the number of input tensors.
  - getInputIndex
```
public int getInputIndex(String opName)
```
    Gets index of an input given the op name of the input.
    IllegalArgumentException will be thrown if the op name does not exist in the model file used to initialize the Interpreter.
  - getInputTensor
```
public Tensor getInputTensor(int inputIndex)
```
    Gets the Tensor associated with the provdied input index.
    IllegalArgumentException will be thrown if the provided index is invalid.
  - getOutputTensorCount
```
public int getOutputTensorCount()
```
    Gets the number of output Tensors.
  - getOutputIndex
```
public int getOutputIndex(String opName)
```
    Gets index of an output given the op name of the output.
    IllegalArgumentException will be thrown if the op name does not exist in the model file used to initialize the Interpreter.
  - getOutputTensor
```
public Tensor getOutputTensor(int outputIndex)
```
    Gets the Tensor associated with the provdied output index.
    IllegalArgumentException will be thrown if the provided index is invalid.
  - getLastNativeInferenceDurationNanoseconds
```
public Long getLastNativeInferenceDurationNanoseconds()
```
    Returns native inference timing.
    IllegalArgumentException will be thrown if the model is not initialized by the Interpreter.
  - setUseNNAPI
```
@Deprecated
public void setUseNNAPI(boolean useNNAPI)
```
    Deprecated. Prefer using Interpreter.Options.setUseNNAPI(boolean) directly for enabling NN API. This method will be removed in a future release.
    
    Turns on/off Android NNAPI for hardware acceleration when it is available.
  - setNumThreads
```
@Deprecated
public void setNumThreads(int numThreads)
```
    Deprecated. Prefer using Interpreter.Options.setNumThreads(int) directly for controlling thread multi-threading. This method will be removed in a future release.
    
    Sets the number of threads to be used for ops that support multi-threading.
  - close
```
public void close()
```
    Release resources associated with the Interpreter.
    
    Specified by:
    
    close in interface AutoCloseable
  - finalize
```
protected void finalize()
                 throws Throwable
```
    Overrides:
    
    finalize in class Object
    
    Throws:
    
    Throwable

Class Interpreter

Nested Class Summary

Constructor Summary

Method Summary

Methods inherited from class java.lang.Object

Constructor Detail

Interpreter

Interpreter

Interpreter

Interpreter

Interpreter

Interpreter

Interpreter

Method Detail

run

runForMultipleInputsOutputs

resizeInput

getInputTensorCount

getInputIndex

getInputTensor

getOutputTensorCount

getOutputIndex

getOutputTensor

getLastNativeInferenceDurationNanoseconds

setUseNNAPI

setNumThreads

close

finalize