Packages

class ConvNetLayer_2D extends AnyRef

The ConvNetLayer_2D class implements a Convolutionsl Net Layer, meant to be part of Convolutionsl Net classifier. The classifier is trained using a data tensor 'x' and a classification vector 'y'. Each row in the tensor is classified into one of 'k' classes numbered '0, ...0, k-1'. Each column, depth in the tensor represents a 2D structure (e.g., an image).

Linear Supertypes
AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. ConvNetLayer_2D
  2. AnyRef
  3. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. Protected

Instance Constructors

  1. new ConvNetLayer_2D(x: Tensor3D, y: VectoI, nf: Int = 5, height: Int = 5, width: Int = 5)

    x

    the input/data 3D tensor with instances stored in rows

    y

    the response/classification vector, where y_i = class for row i of matrix x

    nf

    the number of filters for this convolutional

    height

    the height of the filters

    width

    the width of the filters

Value Members

  1. def filter(i: Int, f: Int): MatriD

    Filter the 'i'-th input matrix with the 'f'-th filter.

    Filter the 'i'-th input matrix with the 'f'-th filter.

    i

    the index of the 'i'th row of the tensor

    f

    the index of the 'f'th filter

  2. def updateFilterParams(f: Int, mat2: MatriD): Unit

    Update filter 'f's parameters.

    Update filter 'f's parameters.

    f

    the index for the filter

    mat2

    the new paramters for the filter's matrix