FractionalAvgPool

public final class FractionalAvgPool

Performs fractional average pooling on the input.

Fractional average pooling is similar to Fractional max pooling in the pooling region generation step. The only difference is that after pooling regions are generated, a mean operation is performed instead of a max operation in each pooling region.

Nested Classes

class FractionalAvgPool.Options Optional attributes for FractionalAvgPool  

Constants

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

Public Methods

Output<TInt64>
colPoolingSequence()
column pooling sequence, needed to calculate gradient.
static <T extends TNumber> FractionalAvgPool<T>
create(Scope scope, Operand<T> value, List<Float> poolingRatio, Options... options)
Factory method to create a class wrapping a new FractionalAvgPool operation.
static FractionalAvgPool.Options
deterministic(Boolean deterministic)
Output<T>
output()
output tensor after fractional avg pooling.
static FractionalAvgPool.Options
overlapping(Boolean overlapping)
static FractionalAvgPool.Options
pseudoRandom(Boolean pseudoRandom)
Output<TInt64>
rowPoolingSequence()
row pooling sequence, needed to calculate gradient.
static FractionalAvgPool.Options
seed(Long seed)
static FractionalAvgPool.Options
seed2(Long seed2)

Inherited Methods

Constants

public static final String OP_NAME

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

Constant Value: "FractionalAvgPool"

Public Methods

public Output<TInt64> colPoolingSequence ()

column pooling sequence, needed to calculate gradient.

public static FractionalAvgPool<T> create (Scope scope, Operand<T> value, List<Float> poolingRatio, Options... options)

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

Parameters
scope current scope
value 4-D with shape `[batch, height, width, channels]`.
poolingRatio Pooling ratio for each dimension of `value`, currently only supports row and col dimension and should be >= 1.0. For example, a valid pooling ratio looks like [1.0, 1.44, 1.73, 1.0]. The first and last elements must be 1.0 because we don't allow pooling on batch and channels dimensions. 1.44 and 1.73 are pooling ratio on height and width dimensions respectively.
options carries optional attributes values
Returns
  • a new instance of FractionalAvgPool

public static FractionalAvgPool.Options deterministic (Boolean deterministic)

Parameters
deterministic When set to True, a fixed pooling region will be used when iterating over a FractionalAvgPool node in the computation graph. Mainly used in unit test to make FractionalAvgPool deterministic.

public Output<T> output ()

output tensor after fractional avg pooling.

public static FractionalAvgPool.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.

public static FractionalAvgPool.Options pseudoRandom (Boolean pseudoRandom)

Parameters
pseudoRandom When set to True, generates the pooling sequence in a pseudorandom fashion, otherwise, in a random fashion. Check paper [Benjamin Graham, Fractional Max-Pooling](http://arxiv.org/abs/1412.6071) for difference between pseudorandom and random.

public Output<TInt64> rowPoolingSequence ()

row pooling sequence, needed to calculate gradient.

public static FractionalAvgPool.Options seed (Long seed)

Parameters
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 FractionalAvgPool.Options seed2 (Long seed2)

Parameters
seed2 An second seed to avoid seed collision.