BiasAddGrad

public final class BiasAddGrad

The backward operation for "BiasAdd" on the "bias" tensor.

It accumulates all the values from out_backprop into the feature dimension. For NHWC data format, the feature dimension is the last. For NCHW data format, the feature dimension is the third-to-last.

Nested Classes

class BiasAddGrad.Options Optional attributes for BiasAddGrad  

Constants

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

Public Methods

Output<T>
asOutput()
Returns the symbolic handle of the tensor.
static <T extends TType> BiasAddGrad<T>
create(Scope scope, Operand<T> outBackprop, Options... options)
Factory method to create a class wrapping a new BiasAddGrad operation.
static BiasAddGrad.Options
dataFormat(String dataFormat)
Output<T>
output()
1-D with size the feature dimension of `out_backprop`.

Inherited Methods

Constants

public static final String OP_NAME

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

Constant Value: "BiasAddGrad"

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 BiasAddGrad<T> create (Scope scope, Operand<T> outBackprop, Options... options)

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

Parameters
scope current scope
outBackprop Any number of dimensions.
options carries optional attributes values
Returns
  • a new instance of BiasAddGrad

public static BiasAddGrad.Options dataFormat (String dataFormat)

Parameters
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> output ()

1-D with size the feature dimension of `out_backprop`.