Index (tflite-native 2.4.1 API)

A B C D F G I M N O Q R S T V

A

addDelegate(Delegate) - Method in class org.tensorflow.lite.Interpreter.Options: Adds a Delegate to be applied during interpreter creation.
allocateTensors() - Method in class org.tensorflow.lite.Interpreter: Expicitly updates allocations for all tensors, if necessary.

B

buffer() - Method in class org.tensorflow.lite.Tensor
byteSize() - Method in enum org.tensorflow.lite.DataType: Returns the size of an element of this type, in bytes, or -1 if element size is variable.

C

close() - Method in class org.tensorflow.lite.Interpreter: Release resources associated with the Interpreter.
close() - Method in class org.tensorflow.lite.Tensor: Disposes of any resources used by the Tensor wrapper.
copyTo(Object) - Method in class org.tensorflow.lite.Tensor: Copies the contents of the tensor to dst and returns dst.
copyTo(Buffer) - Method in class org.tensorflow.lite.Tensor

D

DataType - Enum in org.tensorflow.lite: Represents the type of elements in a TensorFlow Lite Tensor as an enum.
dataType() - Method in class org.tensorflow.lite.Tensor: Returns the DataType of elements stored in the Tensor.
Delegate - Interface in org.tensorflow.lite: Wrapper for a native TensorFlow Lite Delegate.

F

finalize() - Method in class org.tensorflow.lite.Interpreter

G

getInputIndex(String) - Method in class org.tensorflow.lite.Interpreter: Gets index of an input given the op name of the input.
getInputTensor(int) - Method in class org.tensorflow.lite.Interpreter: Gets the Tensor associated with the provdied input index.
getInputTensorCount() - Method in class org.tensorflow.lite.Interpreter: Gets the number of input tensors.
getLastNativeInferenceDurationNanoseconds() - Method in class org.tensorflow.lite.Interpreter: Returns native inference timing.
getNativeHandle() - Method in interface org.tensorflow.lite.Delegate: Returns a native handle to the TensorFlow Lite delegate implementation.
getOutputIndex(String) - Method in class org.tensorflow.lite.Interpreter: Gets index of an output given the op name of the output.
getOutputTensor(int) - Method in class org.tensorflow.lite.Interpreter: Gets the Tensor associated with the provdied output index.
getOutputTensorCount() - Method in class org.tensorflow.lite.Interpreter: Gets the number of output Tensors.
getScale() - Method in class org.tensorflow.lite.Tensor.QuantizationParams: Returns the scale value.
getZeroPoint() - Method in class org.tensorflow.lite.Tensor.QuantizationParams: Returns the zero point value.

I

index() - Method in class org.tensorflow.lite.Tensor: Returns the (global) index of the tensor within the owning Interpreter.
init() - Static method in class org.tensorflow.lite.TensorFlowLite: Ensure the TensorFlowLite native library has been loaded.
Interpreter - Class in org.tensorflow.lite: Driver class to drive model inference with TensorFlow Lite.
Interpreter(File) - Constructor for class org.tensorflow.lite.Interpreter: Initializes a Interpreter
Interpreter(File, int) - Constructor for class org.tensorflow.lite.Interpreter: Deprecated.
Prefer using the Interpreter(File,Options) constructor. This method will be removed in a future release.
Interpreter(File, Interpreter.Options) - Constructor for class org.tensorflow.lite.Interpreter: Initializes a Interpreter and specifies the number of threads used for inference.
Interpreter(ByteBuffer) - Constructor for class org.tensorflow.lite.Interpreter: Initializes a Interpreter with a ByteBuffer of a model file.
Interpreter(ByteBuffer, int) - Constructor for class org.tensorflow.lite.Interpreter: Deprecated.
Prefer using the Interpreter(ByteBuffer,Options) constructor. This method will be removed in a future release.
Interpreter(MappedByteBuffer) - Constructor for class org.tensorflow.lite.Interpreter: Deprecated.
Prefer using the Interpreter(ByteBuffer,Options) constructor. This method will be removed in a future release.
Interpreter(ByteBuffer, Interpreter.Options) - Constructor for class org.tensorflow.lite.Interpreter: Initializes a Interpreter with a ByteBuffer of a model file and a set of custom Interpreter.Options.
Interpreter.Options - Class in org.tensorflow.lite: An options class for controlling runtime interpreter behavior.

M

modifyGraphWithDelegate(Delegate) - Method in class org.tensorflow.lite.Interpreter: Deprecated.
Prefer using Interpreter.Options.addDelegate(org.tensorflow.lite.Delegate) to provide delegates at creation time. This method will be removed in a future release.

N

name() - Method in class org.tensorflow.lite.Tensor: Returns the name of the tensor within the owning Interpreter.
nativeRuntimeVersion() - Static method in class org.tensorflow.lite.TensorFlowLite
nativeSchemaVersion() - Static method in class org.tensorflow.lite.TensorFlowLite
numBytes() - Method in class org.tensorflow.lite.Tensor: Returns the size, in bytes, of the tensor data.
numDimensions() - Method in class org.tensorflow.lite.Tensor: Returns the number of dimensions (sometimes referred to as rank) of the Tensor.
numElements() - Method in class org.tensorflow.lite.Tensor: Returns the number of elements in a flattened (1-D) view of the tensor.

O

Options() - Constructor for class org.tensorflow.lite.Interpreter.Options
org.tensorflow.lite - package org.tensorflow.lite: Defines classes to load and execute TensorFlowLite models.

Q

quantizationParams() - Method in class org.tensorflow.lite.Tensor: Returns the quantization parameters of the tensor within the owning Interpreter.
QuantizationParams(float, int) - Constructor for class org.tensorflow.lite.Tensor.QuantizationParams: Creates a Tensor.QuantizationParams with scale and zero_point.

R

resetVariableTensors() - Method in class org.tensorflow.lite.Interpreter: Advanced: Resets all variable tensors to the default value.
resizeInput(int, int[]) - Method in class org.tensorflow.lite.Interpreter: Resizes idx-th input of the native model to the given dims.
resizeInput(int, int[], boolean) - Method in class org.tensorflow.lite.Interpreter: Resizes idx-th input of the native model to the given dims.
run(Object) - Method in class org.tensorflow.lite.Interpreter: Runs model inference if the model takes only one input, and provides only one output.
runForMultipleInputsOutputs(Object[]) - Method in class org.tensorflow.lite.Interpreter: Runs model inference if the model takes multiple inputs, or returns multiple outputs.
runtimeVersion() - Static method in class org.tensorflow.lite.TensorFlowLite: Returns the version of the underlying TensorFlowLite runtime.

S

schemaVersion() - Static method in class org.tensorflow.lite.TensorFlowLite: Returns the version of the underlying TensorFlowLite model schema.
setAllowBufferHandleOutput(boolean) - Method in class org.tensorflow.lite.Interpreter.Options: Advanced: Set if buffer handle output is allowed.
setCancellable(boolean) - Method in class org.tensorflow.lite.Interpreter.Options: Advanced: Set if the interpreter is able to be cancelled.
setCancelled(boolean) - Method in class org.tensorflow.lite.Interpreter: Advanced: Interrupts inference in the middle of a call to Interpreter.run(java.lang.Object).
setNumThreads(int) - Method in class org.tensorflow.lite.Interpreter.Options: Sets the number of threads to be used for ops that support multi-threading.
setNumThreads(int) - Method in class org.tensorflow.lite.Interpreter: Deprecated.
Prefer using Interpreter.Options.setNumThreads(int) directly for controlling thread multi-threading. This method will be removed in a future release.
setTo(Object) - Method in class org.tensorflow.lite.Tensor: Copies the contents of the provided src object to the Tensor.
setTo(Buffer) - Method in class org.tensorflow.lite.Tensor
setUseNNAPI(boolean) - Method in class org.tensorflow.lite.Interpreter.Options: Sets whether to use NN API (if available) for op execution.
setUseXNNPACK(boolean) - Method in class org.tensorflow.lite.Interpreter.Options: Experimental: Enable an optimized set of floating point CPU kernels (provided by XNNPACK).
shape() - Method in class org.tensorflow.lite.Tensor: Returns the shape of the Tensor, i.e., the sizes of each dimension.
shapeSignature() - Method in class org.tensorflow.lite.Tensor: Returns the original shape of the Tensor, i.e., the sizes of each dimension - before any resizing was performed.

T

Tensor - Class in org.tensorflow.lite: A typed multi-dimensional array used in Tensorflow Lite.
Tensor.QuantizationParams - Class in org.tensorflow.lite: Quantization parameters that corresponds to the table, QuantizationParameters, in the TFLite Model schema file.
TensorFlowLite - Class in org.tensorflow.lite: Static utility methods loading the TensorFlowLite runtime.

V

valueOf(String) - Static method in enum org.tensorflow.lite.DataType: Returns the enum constant of this type with the specified name.
values() - Static method in enum org.tensorflow.lite.DataType: Returns an array containing the constants of this enum type, in the order they are declared.
version() - Static method in class org.tensorflow.lite.TensorFlowLite: Deprecated.
Prefer using or #schemaVersion().

A B C D F G I M N O Q R S T V