• package root
    Definition Classes
  • package lamp

    Lamp provides utilities to build state of the art machine learning applications

    Lamp provides utilities to build state of the art machine learning applications


    Notable types and packages:

    • lamp.STen is a memory managed wrapper around aten.ATen, an off the heap, native n-dimensionl array backed by libtorch.
    • lamp.autograd implements reverse mode automatic differentiation.
    • lamp.nn contains neural network building blocks, see e.g. lamp.nn.Linear.
    • implements a training loop and other data related abstractions.
    • lamp.knn implements k-nearest neighbor search on the CPU and GPU
    • lamp.umap.Umap implements the UMAP dimension reduction algorithm
    • lamp.onnx implements serialization of computation graphs into ONNX format
    • contains CSV and NPY readers
    How to get data into lamp

    Use one of the file readers in or one of the factories in lamp.STen$.

    How to define a custom neural network layer

    See the documentation on lamp.nn.GenericModule

    How to compose neural network layers

    See the documentation on lamp.nn

    How to train models

    See the training loops in

    Definition Classes
  • package nn

    Provides building blocks for neural networks

    Provides building blocks for neural networks

    Notable types:


    Modules facilitating composing other modules:

    • nn.Sequential composes a homogenous list of modules (analogous to List)
    • nn.sequence composes a heterogeneous list of modules (analogous to tuples)
    • nn.EitherModule composes two modules in a scala.Either

    Examples of neural network building blocks, layers etc:

    Definition Classes
  • package bert
    Definition Classes
  • package graph
    Definition Classes
  • GCN
  • Graph
  • GraphAttention
  • MPNN
  • VertexPooling
  • package languagemodel
    Definition Classes



package graph

Linear Supertypes
AnyRef, Any
  1. Alphabetic
  2. By Inheritance
  1. graph
  2. AnyRef
  3. Any
  1. Hide All
  2. Show All
  1. Public
  2. Protected

Type Members

  1. case class GCN[M <: Module](transform: M with Module) extends GraphModule with Product with Serializable
  2. case class Graph(nodeFeatures: Variable, edgeFeatures: Variable, edgeI: STen, edgeJ: STen, vertexPoolingIndices: STen) extends Product with Serializable
  3. case class GraphAttention(wNodeKey1: Constant, wNodeKey2: Constant, wEdgeKey: Constant, wNodeValue: Constant, wAttention: Option[Constant], nonLinearity: Boolean, dropout: Dropout, numHeads: Int) extends GenericModule[Graph, Graph] with Product with Serializable
  4. type GraphModule = GenericModule[Graph, Graph]
  5. case class MPNN[M1 <: Module, M2 <: Module](messageTransform: M1 with Module, vertexTransform: M2 with Module, degreeNormalizeI: Boolean = true, degreeNormalizeJ: Boolean = true, aggregateJ: Boolean = true) extends GraphModule with Product with Serializable

Value Members

  1. object GCN extends Serializable
  2. object GraphAttention extends Serializable
  3. object MPNN extends Serializable
  4. object VertexPooling

Inherited from AnyRef

Inherited from Any