U
- data type for output()
output@Operator(group="random") public final class ParameterizedTruncatedNormal<U extends Number> extends PrimitiveOp implements Operand<U>
scalar which applies to the entire output, or a vector of length shape[0] which stores the parameters for each batch.
Modifier and Type | Class and Description |
---|---|
static class |
ParameterizedTruncatedNormal.Options
Optional attributes for
ParameterizedTruncatedNormal |
operation
Modifier and Type | Method and Description |
---|---|
Output<U> |
asOutput()
Returns the symbolic handle of a tensor.
|
static <U extends Number,T extends Number> |
create(Scope scope,
Operand<T> shape,
Operand<U> means,
Operand<U> stdevs,
Operand<U> minvals,
Operand<U> maxvals,
ParameterizedTruncatedNormal.Options... options)
Factory method to create a class wrapping a new ParameterizedTruncatedNormal operation.
|
Output<U> |
output()
A matrix of shape num_batches x samples_per_batch, filled with random
truncated normal values using the parameters for each row.
|
static ParameterizedTruncatedNormal.Options |
seed(Long seed) |
static ParameterizedTruncatedNormal.Options |
seed2(Long seed2) |
equals, hashCode, op, toString
public static <U extends Number,T extends Number> ParameterizedTruncatedNormal<U> create(Scope scope, Operand<T> shape, Operand<U> means, Operand<U> stdevs, Operand<U> minvals, Operand<U> maxvals, ParameterizedTruncatedNormal.Options... options)
scope
- current scopeshape
- The shape of the output tensor. Batches are indexed by the 0th dimension.means
- The mean parameter of each batch.stdevs
- The standard deviation parameter of each batch. Must be greater than 0.minvals
- The minimum cutoff. May be -infinity.maxvals
- The maximum cutoff. May be +infinity, and must be more than the minval
for each batch.options
- carries optional attributes valuespublic static ParameterizedTruncatedNormal.Options seed(Long seed)
seed
- If either `seed` or `seed2` are set to be non-zero, the random number
generator is seeded by the given seed. Otherwise, it is seeded by a
random seed.public static ParameterizedTruncatedNormal.Options seed2(Long seed2)
seed2
- A second seed to avoid seed collision.public Output<U> output()
public Output<U> asOutput()
Operand
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.
asOutput
in interface Operand<U extends Number>
OperationBuilder.addInput(Output)
Copyright © 2022. All rights reserved.