Outputs random 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.
Public Methods
Output <U> |
asOutput
()
Returns the symbolic handle of a tensor.
|
static <U, T> StatefulTruncatedNormal <U> | |
static <T> StatefulTruncatedNormal <Float> | |
Output <U> |
output
()
Random values with specified shape.
|
Inherited Methods
Public Methods
public Output <U> asOutput ()
Returns the symbolic handle of a 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 StatefulTruncatedNormal <U> create ( Scope scope, Operand <?> resource, Operand <Long> algorithm, Operand <T> shape, Class<U> dtype)
Factory method to create a class wrapping a new StatefulTruncatedNormal operation.
Parameters
scope | current scope |
---|---|
resource | The handle of the resource variable that stores the state of the RNG. |
algorithm | The RNG algorithm. |
shape | The shape of the output tensor. |
dtype | The type of the output. |
Returns
- a new instance of StatefulTruncatedNormal
public static StatefulTruncatedNormal <Float> create ( Scope scope, Operand <?> resource, Operand <Long> algorithm, Operand <T> shape)
Factory method to create a class wrapping a new StatefulTruncatedNormal operation using default output types.
Parameters
scope | current scope |
---|---|
resource | The handle of the resource variable that stores the state of the RNG. |
algorithm | The RNG algorithm. |
shape | The shape of the output tensor. |
Returns
- a new instance of StatefulTruncatedNormal