org.tensorflow.op.nn

Class DepthwiseConv2dNativeBackpropInput<T extends TNumber>

java.lang.Object

org.tensorflow.op.RawOp

org.tensorflow.op.nn.DepthwiseConv2dNativeBackpropInput<T>

Type Parameters:

T - data type for output output

All Implemented Interfaces:

org.tensorflow.ndarray.Shaped, Op, Operand<T>

@Operator(group="nn")
public final class DepthwiseConv2dNativeBackpropInput<T extends TNumber>
extends RawOp
implements Operand<T>

Computes the gradients of depthwise convolution with respect to the input.

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	DepthwiseConv2dNativeBackpropInput.Inputs<T extends TNumber>
static class	DepthwiseConv2dNativeBackpropInput.Options Optional attributes for DepthwiseConv2dNativeBackpropInput

Field Summary

Fields

Modifier and Type	Field and Description
static String	OP_NAME The name of this op, as known by TensorFlow core engine

Fields inherited from class org.tensorflow.op.RawOp

operation

Constructor Summary

Constructors

Constructor and Description
DepthwiseConv2dNativeBackpropInput(Operation operation)

Method Summary

Modifier and Type	Method and Description
Output<T>	asOutput() Returns the symbolic handle of the tensor.
static <T extends TNumber> DepthwiseConv2dNativeBackpropInput<T>	create(Scope scope, Operand<TInt32> inputSizes, Operand<T> filter, Operand<T> outBackprop, List<Long> strides, String padding, DepthwiseConv2dNativeBackpropInput.Options... options) Factory method to create a class wrapping a new DepthwiseConv2dNativeBackpropInput operation.
static DepthwiseConv2dNativeBackpropInput.Options	dataFormat(String dataFormat) Sets the dataFormat option.
static DepthwiseConv2dNativeBackpropInput.Options	dilations(List<Long> dilations) Sets the dilations option.
static DepthwiseConv2dNativeBackpropInput.Options	dilations(Long... dilations) Sets the dilations option.
static DepthwiseConv2dNativeBackpropInput.Options	explicitPaddings(List<Long> explicitPaddings) Sets the explicitPaddings option.
static DepthwiseConv2dNativeBackpropInput.Options	explicitPaddings(Long... explicitPaddings) Sets the explicitPaddings option.
Output<T>	output() Gets output.

Methods inherited from class org.tensorflow.op.RawOp

equals, hashCode, op, toString

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.tensorflow.Operand

asTensor, shape, type

Methods inherited from interface org.tensorflow.op.Op

env, op

Methods inherited from interface org.tensorflow.ndarray.Shaped

rank, size

Field Detail

OP_NAME

public static final String OP_NAME

The name of this op, as known by TensorFlow core engine

See Also:

Constant Field Values

Constructor Detail

DepthwiseConv2dNativeBackpropInput

public DepthwiseConv2dNativeBackpropInput(Operation operation)

Method Detail

create

@Endpoint(describeByClass=true)
public static <T extends TNumber> DepthwiseConv2dNativeBackpropInput<T> create(Scope scope,
                                                                                                               Operand<TInt32> inputSizes,
                                                                                                               Operand<T> filter,
                                                                                                               Operand<T> outBackprop,
                                                                                                               List<Long> strides,
                                                                                                               String padding,
                                                                                                               DepthwiseConv2dNativeBackpropInput.Options... options)

Factory method to create a class wrapping a new DepthwiseConv2dNativeBackpropInput operation.

Type Parameters:

T - data type for DepthwiseConv2dNativeBackpropInput output and operands

Parameters:

scope - current scope

inputSizes - An integer vector representing the shape of input, based on data_format. For example, if data_format is 'NHWC' then input is a 4-D [batch, height, width, channels] tensor.

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

outBackprop - 4-D with shape based on data_format. For example, if data_format is 'NHWC' then out_backprop shape is [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.

padding - The type of padding algorithm to use.

options - carries optional attribute values

Returns:

a new instance of DepthwiseConv2dNativeBackpropInput

explicitPaddings

public static DepthwiseConv2dNativeBackpropInput.Options explicitPaddings(List<Long> explicitPaddings)

Sets the explicitPaddings option.

Parameters:

explicitPaddings - the explicitPaddings option

Returns:

this Options instance.

explicitPaddings

public static DepthwiseConv2dNativeBackpropInput.Options explicitPaddings(Long... explicitPaddings)

Sets the explicitPaddings option.

Parameters:

explicitPaddings - the explicitPaddings option

Returns:

this Options instance.

dataFormat

public static DepthwiseConv2dNativeBackpropInput.Options dataFormat(String dataFormat)

Sets the dataFormat option.

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, height, width, channels]. Alternatively, the format could be "NCHW", the data storage order of: [batch, channels, height, width].

Returns:

this Options instance.

dilations

public static DepthwiseConv2dNativeBackpropInput.Options dilations(List<Long> dilations)

Sets the dilations option.

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.

Returns:

this Options instance.

dilations

public static DepthwiseConv2dNativeBackpropInput.Options dilations(Long... dilations)

Sets the dilations option.

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.

Returns:

this Options instance.

output

public Output<T> output()

Gets output. 4-D with shape according to data_format. For example, if data_format is 'NHWC', output shape is [batch, in_height, in_width, in_channels]. Gradient w.r.t. the input of the convolution.

Returns:

output.

asOutput

public Output<T> asOutput()

Description copied from interface: Operand

Returns the symbolic handle of the 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 TNumber>

See Also:

OperationBuilder.addInput(Output)