Conv1D

@frozen
public struct Conv1D<Scalar> : Layer where Scalar : TensorFlowFloatingPoint

A 1-D convolution layer (e.g. temporal convolution over a time-series).

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

  • The 3-D convolution filter.

    Declaration

    public var filter: Tensor<Scalar>
  • The bias vector.

    Declaration

    public var bias: Tensor<Scalar>
  • The element-wise activation function.

    Declaration

    @noDerivative
    public let activation: Activation
  • The stride of the sliding window for the temporal dimension.

    Declaration

    @noDerivative
    public let stride: Int
  • The padding algorithm for convolution.

    Declaration

    @noDerivative
    public let padding: Padding
  • The dilation factor for the temporal dimension.

    Declaration

    @noDerivative
    public let dilation: Int
  • The element-wise activation function type.

    Declaration

    public typealias Activation = @differentiable (Tensor<Scalar>) -> Tensor<Scalar>
  • Creates a Conv1D layer with the specified filter, bias, activation function, stride, dilation and padding.

    Declaration

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

    Parameters

    filter

    The 3-D convolution filter of shape [filter width, input channel count, output channel count].

    bias

    The bias vector of shape [output channel count].

    activation

    The element-wise activation function.

    stride

    The stride of the sliding window for the temporal dimension.

    padding

    The padding algorithm for convolution.

    dilation

    The dilation factor for the temporal dimension.

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

    The output width is computed as:

    output width = (input width + 2 * padding size - (dilation * (filter width - 1) + 1)) / stride + 1

    and padding size is determined by the padding scheme.

    Note

    Padding size equals zero when using .valid.

    Declaration

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

    Parameters

    input

    The input to the layer [batch size, input width, input channel count].

    Return Value

    The output of shape [batch size, output width, output channel count].

  • Creates a Conv1D layer with the specified filter shape, stride, padding, dilation and element-wise activation function.

    Declaration

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

    Parameters

    filterShape

    The 3-D shape of the filter, representing (filter width, input channel count, output channel count).

    stride

    The stride of the sliding window for the temporal dimension.

    padding

    The padding algorithm for convolution.

    dilation

    The dilation factor for the temporal dimension.

    activation

    The element-wise activation function.

    filterInitializer

    Initializer to use for the filter parameters.

    biasInitializer

    Initializer to use for the bias parameters.