T
- data type for output()
outputpublic final class FractionalAvgPoolGrad<T extends Number> extends PrimitiveOp implements Operand<T>
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.
Modifier and Type | Class and Description |
---|---|
static class |
FractionalAvgPoolGrad.Options
Optional attributes for
FractionalAvgPoolGrad |
operation
Modifier and Type | Method and Description |
---|---|
Output<T> |
asOutput()
Returns the symbolic handle of a tensor.
|
static <T extends Number> |
create(Scope scope,
Operand<Long> origInputTensorShape,
Operand<T> outBackprop,
Operand<Long> rowPoolingSequence,
Operand<Long> colPoolingSequence,
FractionalAvgPoolGrad.Options... options)
Factory method to create a class wrapping a new FractionalAvgPoolGrad operation.
|
Output<T> |
output()
4-D.
|
static FractionalAvgPoolGrad.Options |
overlapping(Boolean overlapping) |
equals, hashCode, op, toString
public static <T extends Number> FractionalAvgPoolGrad<T> create(Scope scope, Operand<Long> origInputTensorShape, Operand<T> outBackprop, Operand<Long> rowPoolingSequence, Operand<Long> colPoolingSequence, FractionalAvgPoolGrad.Options... options)
scope
- current scopeorigInputTensorShape
- 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 valuespublic static FractionalAvgPoolGrad.Options overlapping(Boolean overlapping)
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 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 extends Number>
OperationBuilder.addInput(Output)
Copyright © 2022. All rights reserved.