Tensor (tflite-native 2.4.1 API)

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

```
public final class Tensor
extends java.lang.Object
```
A typed multi-dimensional array used in Tensorflow Lite.
The native handle of a Tensor is managed by NativeInterpreterWrapper, and does not needed to be closed by the client. However, once the NativeInterpreterWrapper has been closed, the tensor handle will be invalidated.

Nested Class Summary

Nested Classes
Modifier and Type	Class and Description
`static class`	`Tensor.QuantizationParams` Quantization parameters that corresponds to the table, `QuantizationParameters`, in the TFLite Model schema file.

Method Summary

All Methods Instance Methods Concrete Methods
Modifier and Type	Method and Description
`java.nio.ByteBuffer`	`buffer()`
`void`	`close()` Disposes of any resources used by the Tensor wrapper.
`void`	`copyTo(java.nio.Buffer dst)`
`java.lang.Object`	`copyTo(java.lang.Object dst)` Copies the contents of the tensor to `dst` and returns `dst`.
`DataType`	`dataType()` Returns the `DataType` of elements stored in the Tensor.
`int`	`index()` Returns the (global) index of the tensor within the owning `Interpreter`.
`java.lang.String`	`name()` Returns the name of the tensor within the owning `Interpreter`.
`int`	`numBytes()` Returns the size, in bytes, of the tensor data.
`int`	`numDimensions()` Returns the number of dimensions (sometimes referred to as rank) of the Tensor.
`int`	`numElements()` Returns the number of elements in a flattened (1-D) view of the tensor.
`Tensor.QuantizationParams`	`quantizationParams()` Returns the quantization parameters of the tensor within the owning `Interpreter`.
`void`	`setTo(java.nio.Buffer src)`
`void`	`setTo(java.lang.Object src)` Copies the contents of the provided `src` object to the Tensor.
`int[]`	`shape()` Returns the shape of the Tensor, i.e., the sizes of each dimension.
`int[]`	`shapeSignature()` Returns the original shape of the Tensor, i.e., the sizes of each dimension - before any resizing was performed.

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

- Method Detail
  - close
```
public void close()
```
    Disposes of any resources used by the Tensor wrapper.
  - dataType
```
public DataType dataType()
```
    Returns the DataType of elements stored in the Tensor.
  - numDimensions
```
public int numDimensions()
```
    Returns the number of dimensions (sometimes referred to as rank) of the Tensor.
    Will be 0 for a scalar, 1 for a vector, 2 for a matrix, 3 for a 3-dimensional tensor etc.
  - numBytes
```
public int numBytes()
```
    Returns the size, in bytes, of the tensor data.
  - numElements
```
public int numElements()
```
    Returns the number of elements in a flattened (1-D) view of the tensor.
  - shape
```
public int[] shape()
```
    Returns the shape of the Tensor, i.e., the sizes of each dimension.
    
    Returns:
    
    an array where the i-th element is the size of the i-th dimension of the tensor.
  - shapeSignature
```
public int[] shapeSignature()
```
    Returns the original shape of the Tensor, i.e., the sizes of each dimension - before any resizing was performed. Unknown dimensions are designated with a value of -1.
    
    Returns:
    
    an array where the i-th element is the size of the i-th dimension of the tensor.
  - index
```
public int index()
```
    Returns the (global) index of the tensor within the owning Interpreter.
  - name
```
public java.lang.String name()
```
    Returns the name of the tensor within the owning Interpreter.
  - quantizationParams
```
public Tensor.QuantizationParams quantizationParams()
```
    Returns the quantization parameters of the tensor within the owning Interpreter.
    Only quantized tensors have valid QuantizationParameters. For tensor that are not quantized, the values of scale and zero_point are both 0.
  - setTo
```
public void setTo(java.lang.Object src)
```
    Copies the contents of the provided src object to the Tensor.
    The src should either be a (multi-dimensional) array with a shape matching that of this tensor, a ByteBuffer of compatible primitive type with a matching flat size, or null iff the tensor has an underlying delegate buffer handle.
    
    Throws:
    
    java.lang.IllegalArgumentException - if the tensor is a scalar or if src is not compatible with the tensor (for example, mismatched data types or shapes).
  - setTo
```
public void setTo(java.nio.Buffer src)
```
  - copyTo
```
public java.lang.Object copyTo(java.lang.Object dst)
```
    Copies the contents of the tensor to dst and returns dst.
    
    Parameters:
    
    dst - the destination buffer, either an explicitly-typed array, a ByteBuffer or null iff the tensor has an underlying delegate buffer handle.
    
    Throws:
    
    java.lang.IllegalArgumentException - if dst is not compatible with the tensor (for example, mismatched data types or shapes).
  - copyTo
```
public void copyTo(java.nio.Buffer dst)
```
  - buffer
```
public java.nio.ByteBuffer buffer()
```

Class Tensor

Nested Class Summary

Method Summary

Methods inherited from class java.lang.Object

Method Detail

close

dataType

numDimensions

numBytes

numElements

shape

shapeSignature

index

name

quantizationParams

setTo

setTo

copyTo

copyTo

buffer