Zeros

public final class Zeros

An operator creating a constant initialized with zeros of the shape given by `dims`.

For example, the following expression

{@code tf.zeros(tf.constant(shape), TFloat32.class)
is the equivalent of
{@code tf.fill(tf.constant(shape), tf.constant(0.0f))

Public Methods

Output<T>
asOutput()
Returns the symbolic handle of the tensor.
static <T extends TType> Zeros<T>
create(Scope scope, Operand<? extends TNumber> dims, Class<T> type)
Creates a zeroed tensor given its type and shape.
Operation
op()
Return this unit of computation as a single Operation.

Inherited Methods

Public Methods

public Output<T> asOutput ()

Returns the symbolic handle of the tensor.

Inputs to TensorFlow operations are outputs of another TensorFlow operation. This method is used to obtain a symbolic handle that represents the computation of the input.

public static Zeros<T> create (Scope scope, Operand<? extends TNumber> dims, Class<T> type)

Creates a zeroed tensor given its type and shape.

Parameters
scope is a scope used to add the underlying operation
dims a 1-D operand that represents the shape of the output tensor
type the output tensor datatype
Returns
  • a constant tensor initialized with zeros
Throws
IllegalArgumentException if the tensor type or shape cannot be initialized with zeros.

public Operation op ()

Return this unit of computation as a single Operation.

For a raw op, the returned value correspond to the TensorFlow operation wrapped by this op.

For a composite op, the returned value usually correspond to the last operation invoked in a chain or to a NoOp grouping one or more operations as a single unit of computation.

Returns