org.tensorflow.op.nn

Class Conv3d<T extends Number>

java.lang.Object

org.tensorflow.op.PrimitiveOp

org.tensorflow.op.nn.Conv3d<T>

Type Parameters:

T - data type for output() output

All Implemented Interfaces:

Op, Operand<T>

@Operator(group="nn")
public final class Conv3d<T extends Number>
extends PrimitiveOp
implements Operand<T>

Computes a 3-D convolution given 5-D `input` and `filter` tensors.

In signal processing, cross-correlation is a measure of similarity of two waveforms as a function of a time-lag applied to one of them. This is also known as a sliding dot product or sliding inner-product.

Our Conv3D implements a form of cross-correlation.

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	Conv3d.Options Optional attributes for Conv3d

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> Conv3d<T>	create(Scope scope, Operand<T> input, Operand<T> filter, List<Long> strides, String padding, Conv3d.Options... options) Factory method to create a class wrapping a new Conv3d operation.
static Conv3d.Options	dataFormat(String dataFormat)
static Conv3d.Options	dilations(List<Long> dilations)
Output<T>	output()

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> Conv3d<T> create(Scope scope,
                                                  Operand<T> input,
                                                  Operand<T> filter,
                                                  List<Long> strides,
                                                  String padding,
                                                  Conv3d.Options... options)

Factory method to create a class wrapping a new Conv3d operation.

Parameters:

scope - current scope

input - Shape `[batch, in_depth, in_height, in_width, in_channels]`.

filter - Shape `[filter_depth, filter_height, filter_width, in_channels, out_channels]`. `in_channels` must match between `input` and `filter`.

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 Conv3d

dataFormat

public static Conv3d.Options dataFormat(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].

dilations

public static Conv3d.Options dilations(List<Long> dilations)

Parameters:

dilations - 1-D tensor of length 5. 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()

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)