org.tensorflow.op.core

Class Conv2DBackpropInput<T extends Number>

java.lang.Object

org.tensorflow.op.PrimitiveOp

org.tensorflow.op.core.Conv2DBackpropInput<T>

Type Parameters:

T - data type for output() output

All Implemented Interfaces:

Op, Operand<T>

@Operator
public final class Conv2DBackpropInput<T extends Number>
extends PrimitiveOp
implements Operand<T>

Computes the gradients of convolution with respect to the input.

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	Conv2DBackpropInput.Options Optional attributes for Conv2DBackpropInput

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> Conv2DBackpropInput<T>	create(Scope scope, Operand<Integer> inputSizes, Operand<T> filter, Operand<T> outBackprop, List<Long> strides, String padding, Conv2DBackpropInput.Options... options) Factory method to create a class to wrap a new Conv2DBackpropInput operation to the graph.
static Conv2DBackpropInput.Options	dataFormat(String dataFormat)
static Conv2DBackpropInput.Options	dilations(List<Long> dilations)
Output<T>	output() 4-D with shape `[batch, in_height, in_width, in_channels]`.
static Conv2DBackpropInput.Options	useCudnnOnGpu(Boolean useCudnnOnGpu)

Methods inherited from class org.tensorflow.op.PrimitiveOp

equals, hashCode, toString

Methods inherited from class java.lang.Object

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

Method Detail

create

public static <T extends Number> Conv2DBackpropInput<T> create(Scope scope,
                                                               Operand<Integer> inputSizes,
                                                               Operand<T> filter,
                                                               Operand<T> outBackprop,
                                                               List<Long> strides,
                                                               String padding,
                                                               Conv2DBackpropInput.Options... options)

Factory method to create a class to wrap a new Conv2DBackpropInput operation to the graph.

Parameters:

scope - current graph scope

inputSizes - An integer vector representing the shape of `input`, where `input` is a 4-D `[batch, height, width, channels]` tensor.

filter - 4-D with shape `[filter_height, filter_width, in_channels, out_channels]`.

outBackprop - 4-D with shape `[batch, out_height, out_width, out_channels]`. Gradients w.r.t. the output of the convolution.

strides - The stride of the sliding window for each dimension of the input of the convolution. Must be in the same order as the dimension specified with format.

padding - The type of padding algorithm to use.

options - carries optional attributes values

Returns:

a new instance of Conv2DBackpropInput

useCudnnOnGpu

public static Conv2DBackpropInput.Options useCudnnOnGpu(Boolean useCudnnOnGpu)

Parameters:

useCudnnOnGpu -

dataFormat

public static Conv2DBackpropInput.Options dataFormat(String dataFormat)

Parameters:

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

dilations

public static Conv2DBackpropInput.Options dilations(List<Long> dilations)

Parameters:

dilations - 1-D tensor of length 4. The dilation factor for each dimension of `input`. If set to k > 1, there will be k-1 skipped cells between each filter element on that dimension. The dimension order is determined by the value of `data_format`, see above for details. Dilations in the batch and depth dimensions must be 1.

output

public Output<T> output()

4-D with shape `[batch, in_height, in_width, in_channels]`. Gradient w.r.t. the input of the convolution.

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)