Package org.tensorflow.op.nn

Class MaxPool3dGrad<U extends java.lang.Number>

java.lang.Object

org.tensorflow.op.PrimitiveOp

org.tensorflow.op.nn.MaxPool3dGrad<U>

Type Parameters:

U - data type for output() output

All Implemented Interfaces:

Op, Operand<U>

@Operator(group="nn")
public final class MaxPool3dGrad<U extends java.lang.Number>
extends PrimitiveOp
implements Operand<U>

Computes gradients of max pooling function.

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	MaxPool3dGrad.Options	Optional attributes for MaxPool3dGrad

Field Summary

Fields inherited from class org.tensorflow.op.PrimitiveOp

operation

Method Summary

Modifier and Type	Method	Description
Output<U>	asOutput()	Returns the symbolic handle of a tensor.
static <U extends java.lang.Number,T extends java.lang.Number> MaxPool3dGrad<U>	create(Scope scope, Operand<T> origInput, Operand<T> origOutput, Operand<U> grad, java.util.List<java.lang.Long> ksize, java.util.List<java.lang.Long> strides, java.lang.String padding, MaxPool3dGrad.Options... options)	Factory method to create a class to wrap a new MaxPool3dGrad operation to the graph.
static MaxPool3dGrad.Options	dataFormat(java.lang.String dataFormat)
Output<U>	output()

Methods inherited from class java.lang.Object

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

Methods inherited from class org.tensorflow.op.PrimitiveOp

equals, hashCode, toString

Method Detail

create

public static <U extends java.lang.Number,T extends java.lang.Number> MaxPool3dGrad<U> create(Scope scope,
                                                                                              Operand<T> origInput,
                                                                                              Operand<T> origOutput,
                                                                                              Operand<U> grad,
                                                                                              java.util.List<java.lang.Long> ksize,
                                                                                              java.util.List<java.lang.Long> strides,
                                                                                              java.lang.String padding,
                                                                                              MaxPool3dGrad.Options... options)

Factory method to create a class to wrap a new MaxPool3dGrad operation to the graph.

Parameters:

scope - current graph scope

origInput - The original input tensor.

origOutput - The original output tensor.

grad - Output backprop of shape `[batch, depth, rows, cols, channels]`.

ksize - 1-D tensor of length 5. The size of the window for each dimension of the input tensor. Must have `ksize[0] = ksize[4] = 1`.

strides - 1-D tensor of length 5. The stride of the sliding window for each dimension of `input`. Must have `strides[0] = strides[4] = 1`.

padding - The type of padding algorithm to use.

options - carries optional attributes values

Returns:

a new instance of MaxPool3dGrad

dataFormat

public static MaxPool3dGrad.Options dataFormat(java.lang.String dataFormat)

Parameters:

dataFormat - The data format of the input and output data. With the default format "NDHWC", the data is stored in the order of: [batch, in_depth, in_height, in_width, in_channels]. Alternatively, the format could be "NCDHW", the data storage order is: [batch, in_channels, in_depth, in_height, in_width].

output

public Output<U> output()

asOutput

public Output<U> 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<U extends java.lang.Number>

See Also:

OperationBuilder.addInput(Output)