org.tensorflow.op.nn

Class MaxPoolGradWithArgmax<T extends Number>

java.lang.Object

org.tensorflow.op.PrimitiveOp

org.tensorflow.op.nn.MaxPoolGradWithArgmax<T>

Type Parameters:

T - data type for output() output

All Implemented Interfaces:

Op, Operand<T>

public final class MaxPoolGradWithArgmax<T extends Number>
extends PrimitiveOp
implements Operand<T>

Computes gradients of the maxpooling function.

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	MaxPoolGradWithArgmax.Options Optional attributes for MaxPoolGradWithArgmax

Field Summary

Fields inherited from class org.tensorflow.op.PrimitiveOp

operation

Method Summary

Modifier and Type	Method and Description
Output<T>	asOutput() Returns the symbolic handle of a tensor.
static <T extends Number,U extends Number> MaxPoolGradWithArgmax<T>	create(Scope scope, Operand<T> input, Operand<T> grad, Operand<U> argmax, List<Long> ksize, List<Long> strides, String padding, MaxPoolGradWithArgmax.Options... options) Factory method to create a class wrapping a new MaxPoolGradWithArgmax operation.
static MaxPoolGradWithArgmax.Options	includeBatchInIndex(Boolean includeBatchInIndex)
Output<T>	output() Gradients w.r.t.

Methods inherited from class org.tensorflow.op.PrimitiveOp

equals, hashCode, op, toString

Methods inherited from class java.lang.Object

clone, finalize, getClass, notify, notifyAll, wait, wait, wait

Method Detail

create

public static <T extends Number,U extends Number> MaxPoolGradWithArgmax<T> create(Scope scope,
                                                                                  Operand<T> input,
                                                                                  Operand<T> grad,
                                                                                  Operand<U> argmax,
                                                                                  List<Long> ksize,
                                                                                  List<Long> strides,
                                                                                  String padding,
                                                                                  MaxPoolGradWithArgmax.Options... options)

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

Parameters:

scope - current scope

input - The original input.

grad - 4-D with shape `[batch, height, width, channels]`. Gradients w.r.t. the output of `max_pool`.

argmax - The indices of the maximum values chosen for each output of `max_pool`.

ksize - The size of the window for each dimension of the input tensor.

strides - The stride of the sliding window for each dimension of the input tensor.

padding - The type of padding algorithm to use.

options - carries optional attributes values

Returns:

a new instance of MaxPoolGradWithArgmax

includeBatchInIndex

public static MaxPoolGradWithArgmax.Options includeBatchInIndex(Boolean includeBatchInIndex)

Parameters:

includeBatchInIndex - Whether to include batch dimension in flattened index of `argmax`.

output

public Output<T> output()

Gradients w.r.t. the input of `max_pool`.

asOutput

public Output<T> asOutput()

Description copied from interface: Operand

Returns the symbolic handle of a 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.

Specified by:

asOutput in interface Operand<T extends Number>

See Also:

OperationBuilder.addInput(Output)