MCPcopy Create free account
hub / github.com/DeepRec-AI/DeepRec / FractionalMaxPool

Function FractionalMaxPool

tensorflow/go/op/wrappers.go:9864–9881  ·  view source on GitHub ↗

Performs fractional max pooling on the input. Fractional max pooling is slightly different than regular max pooling. In regular max pooling, you downsize an input set by taking the maximum value of smaller N x N subsections of the set (often 2x2), and try to reduce the set by a factor of N, where

(scope *Scope, value tf.Output, pooling_ratio []float32, optional ...FractionalMaxPoolAttr)

Source from the content-addressed store, hash-verified

9862//
9863// Returns output tensor after fractional max pooling.row pooling sequence, needed to calculate gradient.column pooling sequence, needed to calculate gradient.
9864func FractionalMaxPool(scope *Scope, value tf.Output, pooling_ratio []float32, optional ...FractionalMaxPoolAttr) (output tf.Output, row_pooling_sequence tf.Output, col_pooling_sequence tf.Output) {
9865 if scope.Err() != nil {
9866 return
9867 }
9868 attrs := map[string]interface{}{"pooling_ratio": pooling_ratio}
9869 for _, a := range optional {
9870 a(attrs)
9871 }
9872 opspec := tf.OpSpec{
9873 Type: "FractionalMaxPool",
9874 Input: []tf.Input{
9875 value,
9876 },
9877 Attrs: attrs,
9878 }
9879 op := scope.AddOperation(opspec)
9880 return op.Output(0), op.Output(1), op.Output(2)
9881}
9882
9883// PrelinearizeTupleAttr is an optional argument to PrelinearizeTuple.
9884type PrelinearizeTupleAttr func(optionalAttr)

Callers 1

TEST_FFunction · 0.85

Calls 4

aClass · 0.85
ErrMethod · 0.45
AddOperationMethod · 0.45
OutputMethod · 0.45

Tested by 1

TEST_FFunction · 0.68