Class Dilation2dBackpropInput.Inputs<T extends TNumber>

java.lang.Object

org.tensorflow.op.RawOpInputs<Dilation2dBackpropInput<T>>

org.tensorflow.op.nn.Dilation2dBackpropInput.Inputs<T>

Enclosing class:

Dilation2dBackpropInput<T extends TNumber>

public static class Dilation2dBackpropInput.Inputs<T extends TNumber>
extends RawOpInputs<Dilation2dBackpropInput<T>>

Field Summary

Fields

Modifier and Type	Field	Description
final Operand<T>	filter	3-D with shape [filter_height, filter_width, depth].
final Operand<T>	input	4-D with shape [batch, in_height, in_width, depth].
final Operand<T>	outBackprop	4-D with shape [batch, out_height, out_width, depth].
final String	padding	The type of padding algorithm to use.
final long[]	rates	1-D of length 4.
final long[]	strides	1-D of length 4.
final DataType	T	The T attribute

Constructor Summary

Constructors

Constructor	Description
Inputs(GraphOperation op)

Method Summary

Methods inherited from class RawOpInputs

attributeMetadata, attributeNames, attributes, attributeValue, attributeValues, equals, getOutputs, hashCode, toString

Methods inherited from class Object

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

Field Details

input

public final Operand<T extends TNumber> input

4-D with shape [batch, in_height, in_width, depth].

filter

public final Operand<T extends TNumber> filter

3-D with shape [filter_height, filter_width, depth].

outBackprop

public final Operand<T extends TNumber> outBackprop

4-D with shape [batch, out_height, out_width, depth].

T

public final DataType T

The T attribute

strides

public final long[] strides

1-D of length 4. The stride of the sliding window for each dimension of the input tensor. Must be: [1, stride_height, stride_width, 1].

rates

public final long[] rates

1-D of length 4. The input stride for atrous morphological dilation. Must be: [1, rate_height, rate_width, 1].

padding

public final String padding

The type of padding algorithm to use.

Constructor Details

Inputs

public Inputs(GraphOperation op)