Tensor

public final class Tensor

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 Classes

class Tensor.QuantizationParams Quantization parameters that corresponds to the table, QuantizationParameters, in the TFLite Model schema file.

Public Methods

ByteBuffer	asReadOnlyBuffer() Returns a read-only `ByteBuffer` view of the tensor data.
DataType	dataType() Returns the `DataType` of elements stored in the Tensor.
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`.
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.

Inherited Methods

From class java.lang.Object

boolean	equals(Object arg0)
final Class<?>	getClass()
int	hashCode()
final void	notify()
final void	notifyAll()
String	toString()
final void	wait(long arg0, int arg1)
final void	wait(long arg0)
final void	wait()

Public Methods

public ByteBuffer asReadOnlyBuffer ()

Returns a read-only ByteBuffer view of the tensor data.

In general, this method is most useful for obtaining a read-only view of output tensor data, *after* inference has been executed (e.g., via Interpreter.run(Object, Object)). In particular, some graphs have dynamically shaped outputs, which can make feeding a predefined output buffer to the Interpreter awkward. Example usage:

interpreter.run(input, null);
 ByteBuffer outputBuffer = interpreter.getOutputTensor(0).asReadOnlyBuffer();
 // Copy or read from outputBuffer.

WARNING: If the tensor has not yet been allocated, e.g., before inference has been executed, the result is undefined. Note that the underlying tensor pointer may also change when the tensor is invalidated in any way (e.g., if inference is executed, or the graph is resized), so it is *not* safe to hold a reference to the returned buffer beyond immediate use directly following inference. Example *bad* usage:

ByteBuffer outputBuffer = interpreter.getOutputTensor(0).asReadOnlyBuffer();
 interpreter.run(input, null);
 // Copy or read from outputBuffer (which may now be invalid).

WARNING: This is an experimental interface that is subject to change.

Throws

IllegalArgumentException	if the tensor data has not been allocated.

public DataType dataType ()

Returns the DataType of elements stored in the Tensor.

public int numBytes ()

Returns the size, in bytes, of the tensor data.

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.

public int numElements ()

Returns the number of elements in a flattened (1-D) view of the tensor.

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.

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.

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.