StatelessTruncatedNormalV2

public final class StatelessTruncatedNormalV2

Outputs deterministic pseudorandom values from a truncated normal distribution.

The generated values follow a normal distribution with mean 0 and standard deviation 1, except that values whose magnitude is more than 2 standard deviations from the mean are dropped and re-picked.

The outputs are a deterministic function of `shape`, `key`, `counter` and `alg`.

Constants

String OP_NAME The name of this op, as known by TensorFlow core engine

Public Methods

Output<U>
asOutput()
Returns the symbolic handle of the tensor.
static <U extends TNumber> StatelessTruncatedNormalV2<U>
create(Scope scope, Operand<? extends TNumber> shape, Operand<?> key, Operand<?> counter, Operand<TInt32> alg, Class<U> dtype)
Factory method to create a class wrapping a new StatelessTruncatedNormalV2 operation.
static StatelessTruncatedNormalV2<TFloat32>
create(Scope scope, Operand<? extends TNumber> shape, Operand<?> key, Operand<?> counter, Operand<TInt32> alg)
Factory method to create a class wrapping a new StatelessTruncatedNormalV2 operation using default output types.
Output<U>
output()
Random values with specified shape.

Inherited Methods

Constants

public static final String OP_NAME

The name of this op, as known by TensorFlow core engine

Constant Value: "StatelessTruncatedNormalV2"

Public Methods

public Output<U> 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 StatelessTruncatedNormalV2<U> create (Scope scope, Operand<? extends TNumber> shape, Operand<?> key, Operand<?> counter, Operand<TInt32> alg, Class<U> dtype)

Factory method to create a class wrapping a new StatelessTruncatedNormalV2 operation.

Parameters
scope current scope
shape The shape of the output tensor.
key Key for the counter-based RNG algorithm (shape uint64[1]).
counter Initial counter for the counter-based RNG algorithm (shape uint64[2] or uint64[1] depending on the algorithm). If a larger vector is given, only the needed portion on the left (i.e. [:N]) will be used.
alg The RNG algorithm (shape int32[]).
dtype The type of the output.
Returns
  • a new instance of StatelessTruncatedNormalV2

public static StatelessTruncatedNormalV2<TFloat32> create (Scope scope, Operand<? extends TNumber> shape, Operand<?> key, Operand<?> counter, Operand<TInt32> alg)

Factory method to create a class wrapping a new StatelessTruncatedNormalV2 operation using default output types.

Parameters
scope current scope
shape The shape of the output tensor.
key Key for the counter-based RNG algorithm (shape uint64[1]).
counter Initial counter for the counter-based RNG algorithm (shape uint64[2] or uint64[1] depending on the algorithm). If a larger vector is given, only the needed portion on the left (i.e. [:N]) will be used.
alg The RNG algorithm (shape int32[]).
Returns
  • a new instance of StatelessTruncatedNormalV2

public Output<U> output ()

Random values with specified shape.