ai.djl.nn.convolutional

Class Conv1dTranspose

java.lang.Object

ai.djl.nn.AbstractBlock

ai.djl.nn.convolutional.Deconvolution

ai.djl.nn.convolutional.Conv1dTranspose

All Implemented Interfaces:

Block

public class Conv1dTranspose
extends Deconvolution

A Conv1dTranspose layer works similar to Deconvolution layer with the exception of the number of dimension it operates on being only one, which is LayoutType.WIDTH. The channel of the input data may be more than one, depending on what data is processed. Each filter slides through the data with only one direction of movement along the dimension itself.

The input to a Conv1dTranspose is an NDList with a single 3-D NDArray. The layout of the NDArray must be "NCW". The shapes are

• data: (batch_size, channel, width)
• weight: (num_filter, channel, kernel[0])
• bias: (num_filter,)
• out: (batch_size, num_filter, out_width)
out_width = f(width, kernel[0], pad[0], oPad[0], stride[0], dilate[0])
where f(x, k, p, oP, s, d) = (x-1)*s-2*p+k+oP

Both weight and bias are learn-able parameters.

See Also:

Deconvolution

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	Conv1dTranspose.Builder The Builder to construct a Conv1dTranspose type of Block.

Nested classes/interfaces inherited from class ai.djl.nn.convolutional.Deconvolution

Deconvolution.DeconvolutionBuilder<T extends Deconvolution.DeconvolutionBuilder>

Field Summary

Fields inherited from class ai.djl.nn.convolutional.Deconvolution

bias, dilation, filters, groups, includeBias, kernelShape, outPadding, padding, stride, weight

Fields inherited from class ai.djl.nn.AbstractBlock

children, inputNames, inputShapes, parameters, parameterShapeCallbacks, version

Method Summary

Modifier and Type	Method and Description
static Conv1dTranspose.Builder	builder() Creates a builder to build a Conv1dTranspose.
static NDList	conv1dTranspose(NDArray input, NDArray weight) Applies 1D deconvolution over an input signal composed of several input planes.
static NDList	conv1dTranspose(NDArray input, NDArray weight, NDArray bias) Applies 1D deconvolution over an input signal composed of several input planes.
static NDList	conv1dTranspose(NDArray input, NDArray weight, NDArray bias, Shape stride) Applies 1D deconvolution over an input signal composed of several input planes.
static NDList	conv1dTranspose(NDArray input, NDArray weight, NDArray bias, Shape stride, Shape padding) Applies 1D deconvolution over an input signal composed of several input planes.
static NDList	conv1dTranspose(NDArray input, NDArray weight, NDArray bias, Shape stride, Shape padding, Shape outPadding) Applies 1D deconvolution over an input signal composed of several input planes.
static NDList	conv1dTranspose(NDArray input, NDArray weight, NDArray bias, Shape stride, Shape padding, Shape outPadding, Shape dilation) Applies 1D deconvolution over an input signal composed of several input planes.
static NDList	conv1dTranspose(NDArray input, NDArray weight, NDArray bias, Shape stride, Shape padding, Shape outPadding, Shape dilation, int groups) Applies 1D convolution over an input signal composed of several input planes.
protected LayoutType[]	getExpectedLayout() Returns the expected layout of the input.
protected java.lang.String	getStringLayout() Returns the string representing the layout of the input.
protected int	numDimensions() Returns the number of dimensions of the input.

Methods inherited from class ai.djl.nn.convolutional.Deconvolution

beforeInitialize, forwardInternal, getOutputShapes, loadMetadata

Methods inherited from class ai.djl.nn.AbstractBlock

addChildBlock, addParameter, addParameter, addParameter, cast, clear, describeInput, forward, getChildren, getDirectParameters, getParameters, getParameterShape, initialize, initializeChildBlocks, isInitialized, loadParameters, readInputShapes, saveInputShapes, saveMetadata, saveParameters, setInitializer, setInitializer, toString

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Methods inherited from interface ai.djl.nn.Block

forward, forward, validateLayout

Method Detail

getExpectedLayout

protected LayoutType[] getExpectedLayout()

Returns the expected layout of the input.

Specified by:

getExpectedLayout in class Deconvolution

Returns:

the expected layout of the input

getStringLayout

protected java.lang.String getStringLayout()

Returns the string representing the layout of the input.

Specified by:

getStringLayout in class Deconvolution

Returns:

the string representing the layout of the input

numDimensions

protected int numDimensions()

Returns the number of dimensions of the input.

Specified by:

numDimensions in class Deconvolution

Returns:

the number of dimensions of the input

conv1dTranspose

public static NDList conv1dTranspose(NDArray input,
                                     NDArray weight)

Applies 1D deconvolution over an input signal composed of several input planes.

Parameters:

input - the input NDArray of shape (batchSize, inputChannel, width)

weight - filters NDArray of shape (outChannel, inputChannel/groups, width)

Returns:

the output of the conv1dTranspose operation

conv1dTranspose

public static NDList conv1dTranspose(NDArray input,
                                     NDArray weight,
                                     NDArray bias)

Applies 1D deconvolution over an input signal composed of several input planes.

Parameters:

input - the input NDArray of shape (batchSize, inputChannel, width)

weight - filters NDArray of shape (outChannel, inputChannel/groups, width)

bias - bias NDArray of shape (outChannel)

Returns:

the output of the conv1dTranspose operation

conv1dTranspose

public static NDList conv1dTranspose(NDArray input,
                                     NDArray weight,
                                     NDArray bias,
                                     Shape stride)

Applies 1D deconvolution over an input signal composed of several input planes.

Parameters:

input - the input NDArray of shape (batchSize, inputChannel, width)

weight - filters NDArray of shape (outChannel, inputChannel/groups, width)

bias - bias NDArray of shape (outChannel)

stride - the stride of the deconvolving kernel: Shape(width)

Returns:

the output of the conv1dTranspose operation

conv1dTranspose

public static NDList conv1dTranspose(NDArray input,
                                     NDArray weight,
                                     NDArray bias,
                                     Shape stride,
                                     Shape padding)

Applies 1D deconvolution over an input signal composed of several input planes.

Parameters:

input - the input NDArray of shape (batchSize, inputChannel, width)

weight - filters NDArray of shape (outChannel, inputChannel/groups, width)

bias - bias NDArray of shape (outChannel)

stride - the stride of the deconvolving kernel: Shape(width)

padding - implicit paddings on both sides of the input: Shape(width)

Returns:

the output of the conv1dTranspose operation

conv1dTranspose

public static NDList conv1dTranspose(NDArray input,
                                     NDArray weight,
                                     NDArray bias,
                                     Shape stride,
                                     Shape padding,
                                     Shape outPadding)

Applies 1D deconvolution over an input signal composed of several input planes.

Parameters:

input - the input NDArray of shape (batchSize, inputChannel, width)

weight - filters NDArray of shape (outChannel, inputChannel/groups, width)

bias - bias NDArray of shape (outChannel)

stride - the stride of the deconvolving kernel: Shape(width)

padding - implicit paddings on both sides of the input: Shape(width)

outPadding - Controls the amount of implicit zero-paddings on both sides of the output for outputPadding number of points for each dimension.

Returns:

the output of the conv1dTranspose operation

conv1dTranspose

public static NDList conv1dTranspose(NDArray input,
                                     NDArray weight,
                                     NDArray bias,
                                     Shape stride,
                                     Shape padding,
                                     Shape outPadding,
                                     Shape dilation)

Applies 1D deconvolution over an input signal composed of several input planes.

Parameters:

input - the input NDArray of shape (batchSize, inputChannel, width)

weight - filters NDArray of shape (outChannel, inputChannel/groups, width)

bias - bias NDArray of shape (outChannel)

stride - the stride of the deconvolving kernel: Shape(width)

padding - implicit paddings on both sides of the input: Shape(width)

outPadding - Controls the amount of implicit zero-paddings on both sides of the output for outputPadding number of points for each dimension.

dilation - the spacing between kernel elements: Shape(width)

Returns:

the output of the conv1dTranspose operation

conv1dTranspose

public static NDList conv1dTranspose(NDArray input,
                                     NDArray weight,
                                     NDArray bias,
                                     Shape stride,
                                     Shape padding,
                                     Shape outPadding,
                                     Shape dilation,
                                     int groups)

Applies 1D convolution over an input signal composed of several input planes.

Parameters:

input - the input NDArray of shape (batchSize, inputChannel, width)

weight - filters NDArray of shape (outChannel, inputChannel/groups, width)

bias - bias NDArray of shape (outChannel)

stride - the stride of the deconvolving kernel: Shape(width)

padding - implicit paddings on both sides of the input: Shape(width)

outPadding - Controls the amount of implicit zero-paddings on both sides of the output for outputPadding number of points for each dimension. Shape(width)

dilation - the spacing between kernel elements: Shape(width)

groups - split input into groups: input channel(input.size(1)) should be divisible by the number of groups

Returns:

the output of the conv1dTranspose operation

builder

public static Conv1dTranspose.Builder builder()

Creates a builder to build a Conv1dTranspose.

Returns:

a new builder