T
- data type for output()
output@Operator(group="nn") public final class BiasAdd<T> extends PrimitiveOp implements Operand<T>
This is a special case of `tf.add` where `bias` is restricted to be 1-D. Broadcasting is supported, so `value` may have any number of dimensions.
Modifier and Type | Class and Description |
---|---|
static class |
BiasAdd.Options
Optional attributes for
BiasAdd |
operation
Modifier and Type | Method and Description |
---|---|
Output<T> |
asOutput()
Returns the symbolic handle of a tensor.
|
static <T> BiasAdd<T> |
create(Scope scope,
Operand<T> value,
Operand<T> bias,
BiasAdd.Options... options)
Factory method to create a class wrapping a new BiasAdd operation.
|
static BiasAdd.Options |
dataFormat(String dataFormat) |
Output<T> |
output()
Broadcasted sum of `value` and `bias`.
|
equals, hashCode, op, toString
public static <T> BiasAdd<T> create(Scope scope, Operand<T> value, Operand<T> bias, BiasAdd.Options... options)
scope
- current scopevalue
- Any number of dimensions.bias
- 1-D with size the last dimension of `value`.options
- carries optional attributes valuespublic static BiasAdd.Options dataFormat(String dataFormat)
dataFormat
- Specify the data format of the input and output data. With the
default format "NHWC", the bias tensor will be added to the last dimension
of the value tensor.
Alternatively, the format could be "NCHW", the data storage order of:
[batch, in_channels, in_height, in_width].
The tensor will be added to "in_channels", the third-to-the-last
dimension.public Output<T> 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<T>
OperationBuilder.addInput(Output)
Copyright © 2022. All rights reserved.