FractionalAvgPoolGrad

public final class FractionalAvgPoolGrad

Computes gradient of the FractionalAvgPool function.

Unlike FractionalMaxPoolGrad, we don't need to find arg_max for FractionalAvgPoolGrad, we just need to evenly back-propagate each element of out_backprop to those indices that form the same pooling cell. Therefore, we just need to know the shape of original input tensor, instead of the whole tensor.

Nested Classes

class FractionalAvgPoolGrad.Options Optional attributes for FractionalAvgPoolGrad

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 > FractionalAvgPoolGrad <T>
create ( Scope scope, Operand < TInt64 > origInputTensorShape, Operand <T> outBackprop, Operand < TInt64 > rowPoolingSequence, Operand < TInt64 > colPoolingSequence, Options... options)
Factory method to create a class wrapping a new FractionalAvgPoolGrad operation.
Output <T>
output ()
4-D.
static FractionalAvgPoolGrad.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: "FractionalAvgPoolGrad"

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 FractionalAvgPoolGrad <T> create ( Scope scope, Operand < TInt64 > origInputTensorShape, Operand <T> outBackprop, Operand < TInt64 > rowPoolingSequence, Operand < TInt64 > colPoolingSequence, Options... options)

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

Parameters
scope current scope
origInputTensorShape Original input tensor shape for `fractional_avg_pool`
outBackprop 4-D with shape `[batch, height, width, channels]`. Gradients w.r.t. the output of `fractional_avg_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 FractionalAvgPoolGrad

public Output <T> output ()

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

public static FractionalAvgPoolGrad.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 [41/3, 26/3] for fractional avg pooling.