Class FractionalAvgPoolGrad.Inputs<T extends TNumber>

java.lang.Object
org.tensorflow.op.RawOpInputs<FractionalAvgPoolGrad<T>>
org.tensorflow.op.nn.FractionalAvgPoolGrad.Inputs<T>
Enclosing class:
FractionalAvgPoolGrad<T extends TNumber>
public static class FractionalAvgPoolGrad.Inputs<T extends TNumber> extends RawOpInputs<FractionalAvgPoolGrad<T>>

  • Field Details

    • origInputTensorShape

      public final Operand<TInt64> origInputTensorShape
      Original input tensor shape for fractional_avg_pool

    • outBackprop

      public final Operand<T extends TNumber> outBackprop
      4-D with shape [batch, height, width, channels]. Gradients w.r.t. the output of fractional_avg_pool.

    • rowPoolingSequence

      public final Operand<TInt64> rowPoolingSequence
      row pooling sequence, form pooling region with col_pooling_sequence.

    • colPoolingSequence

      public final Operand<TInt64> colPoolingSequence
      column pooling sequence, form pooling region with row_pooling sequence.

    • overlapping

      public final boolean 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.

    • T

      public final DataType T
      The T attribute

  • Constructor Details