Package org.apache.spark.ml.ann

Interface Layer

All Superinterfaces:
Serializable
public interface Layer extends Serializable
Trait that holds Layer properties, that are needed to instantiate it. Implements Layer instantiation.

  • Method Summary

    Modifier and Type
    Method
    Description
    LayerModel
    createModel(breeze.linalg.DenseVector<Object> initialWeights)
    Returns the instance of the layer based on weights provided.
    int
    getOutputSize(int inputSize)
    Returns the output size given the input size (not counting the stack size).
    LayerModel
    initModel(breeze.linalg.DenseVector<Object> weights, Random random)
    Returns the instance of the layer with random generated weights.
    boolean
    inPlace()
    If true, the memory is not allocated for the output of this layer.
    int
    weightSize()
    Number of weights that is used to allocate memory for the weights vector

  • Method Details

    • createModel

      LayerModel createModel(breeze.linalg.DenseVector<Object> initialWeights)
      Returns the instance of the layer based on weights provided. Size of weights must be equal to weightSize

      Parameters:
      initialWeights - vector with layer weights
      Returns:
      the layer model

    • getOutputSize

      int getOutputSize(int inputSize)
      Returns the output size given the input size (not counting the stack size). Output size is used to allocate memory for the output.

      Parameters:
      inputSize - input size
      Returns:
      output size

    • inPlace

      boolean inPlace()
      If true, the memory is not allocated for the output of this layer. The memory allocated to the previous layer is used to write the output of this layer. Developer can set this to true if computing delta of a previous layer does not involve its output, so the current layer can write there. This also mean that both layers have the same number of outputs.
      Returns:
      (undocumented)

    • initModel

      LayerModel initModel(breeze.linalg.DenseVector<Object> weights, Random random)
      Returns the instance of the layer with random generated weights.

      Parameters:
      weights - vector for weights initialization, must be equal to weightSize
      random - random number generator
      Returns:
      the layer model

    • weightSize

      int weightSize()
      Number of weights that is used to allocate memory for the weights vector
      Returns:
      (undocumented)