TransposedConv3D

@frozen
public struct TransposedConv3D<Scalar> : Layer where Scalar : TensorFlowFloatingPoint

A 3-D transposed convolution layer (e.g. spatial transposed convolution over images).

This layer creates a convolution filter that is transpose-convolved with the layer input to produce a tensor of outputs.

• filter

  The 5-D convolution kernel.

  Declaration

  public var filter: Tensor<Scalar>

• bias

  The bias vector.

  Declaration

  public var bias: Tensor<Scalar>

• activation

  The element-wise activation function.

  Declaration

  @noDerivative
  public let activation: Activation

• strides

  The strides of the sliding window for spatial dimensions.

  Declaration

  @noDerivative
  public let strides: (Int, Int, Int)

• padding

  The padding algorithm for convolution.

  Declaration

  @noDerivative
  public let padding: Padding

• paddingIndex

  The paddingIndex property allows us to handle computation based on padding.

  Declaration

  @noDerivative
  public let paddingIndex: Int

• Activation

  The element-wise activation function type.

  Declaration

  public typealias Activation = @differentiable (Tensor<Scalar>) -> Tensor<Scalar>

• init(filter:bias:activation:strides:padding:)

  Creates a TransposedConv3D layer with the specified filter, bias, activation function, strides, and padding.

  Declaration

  public init(
    filter: Tensor<Scalar>,
    bias: Tensor<Scalar>? = nil,
    activation: @escaping Activation = identity,
    strides: (Int, Int, Int) = (1, 1, 1),
    padding: Padding = .valid
  )

  Parameters

  filter	The 5-D convolution kernel.
  bias	The bias vector.
  activation	The element-wise activation function.
  strides	The strides of the sliding window for spatial dimensions.
  padding	The padding algorithm for convolution.

• forward(_:)

  Returns the output obtained from applying the layer to the given input.

  Declaration

  @differentiable
  public func forward(_ input: Tensor<Scalar>) -> Tensor<Scalar>

  Parameters

  input

  The input to the layer.

  Return Value

  The output.

• init(filterShape:strides:padding:activation:useBias:filterInitializer:biasInitializer:)

  Creates a TransposedConv3D layer with the specified filter shape, strides, padding, and element-wise activation function. The filter tensor is initialized using Glorot uniform initialization with the specified generator. The bias vector is initialized with zeros.

  Declaration

  public init(
    filterShape: (Int, Int, Int, Int, Int),
    strides: (Int, Int, Int) = (1, 1, 1),
    padding: Padding = .valid,
    activation: @escaping Activation = identity,
    useBias: Bool = true,
    filterInitializer: ParameterInitializer<Scalar> = glorotUniform(),
    biasInitializer: ParameterInitializer<Scalar> = zeros()
  )

  Parameters

  filterShape	The shape of the 5-D convolution kernel.
  strides	The strides of the sliding window for spatial dimensions.
  padding	The padding algorithm for convolution.
  activation	The element-wise activation function.
  generator	The random number generator for initialization.