Have a question? Connect with the community at the TensorFlow Forum Visit Forum

FractionalMaxPoolGrad

public final class FractionalMaxPoolGrad

Computes gradient of the FractionalMaxPool function.

Nested Classes

class FractionalMaxPoolGrad.Options Optional attributes for FractionalMaxPoolGrad

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 TNumber > FractionalMaxPoolGrad <T>
create ( Scope scope, Operand <T> origInput, Operand <T> origOutput, Operand <T> outBackprop, Operand < TInt64 > rowPoolingSequence, Operand < TInt64 > colPoolingSequence, Options... options)
Factory method to create a class wrapping a new FractionalMaxPoolGrad operation.
Output <T>
output ()
4-D.
static FractionalMaxPoolGrad.Options
overlapping (Boolean overlapping)

Inherited Methods

Constants

public static final String OP_NAME

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

Constant Value: "FractionalMaxPoolGrad"

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 FractionalMaxPoolGrad <T> create ( Scope scope, Operand <T> origInput, Operand <T> origOutput, Operand <T> outBackprop, Operand < TInt64 > rowPoolingSequence, Operand < TInt64 > colPoolingSequence, Options... options)

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

Parameters
scope current scope
origInput Original input for `fractional_max_pool`
origOutput Original output for `fractional_max_pool`
outBackprop 4-D with shape `[batch, height, width, channels]`. Gradients w.r.t. the output of `fractional_max_pool`.
rowPoolingSequence row pooling sequence, form pooling region with col_pooling_sequence.
colPoolingSequence column pooling sequence, form pooling region with row_pooling sequence.
options carries optional attributes values
Returns
  • a new instance of FractionalMaxPoolGrad

public Output <T> output ()

4-D. Gradients w.r.t. the input of `fractional_max_pool`.

public static FractionalMaxPoolGrad.Options overlapping (Boolean overlapping)

Parameters
overlapping When set to True, it means when pooling, the values at the boundary of adjacent pooling cells are used by both cells. For example:

`index 0 1 2 3 4`

`value 20 5 16 3 7`

If the pooling sequence is [0, 2, 4], then 16, at index 2 will be used twice. The result would be [20, 16] for fractional max pooling.