TorchLean API

Docs HomeGuideExamplesGraphs

NN.API.Models.Mlp

MLP Model Helpers (API) #

Compact, reusable MLP-shaped model constructors for TorchLean examples.

These live in the API layer so runnable examples can stay focused on: data loading, training loops, and CLI flags, rather than repeating the same linear → activation → linear boilerplate.

Scope note: these are building blocks, not pretrained checkpoints.

source
structure NN.API.nn.models.Mlp1Config :
Type

Configuration for a single-hidden-layer MLP over batched row vectors.

Instances For
    source
    def NN.API.nn.models.instReprMlp1Config.repr :
    Mlp1Config → ℕ → Std.Format
    Instances For
      source
      @[implicit_reducible]
      instance NN.API.nn.models.instReprMlp1Config :
      Repr Mlp1Config
      source
      @[reducible, inline]
      abbrev NN.API.nn.models.mlp1InShape (cfg : Mlp1Config) :
      Shape

      Input shape (batch × inDim) for an Mlp1Config.

      Instances For
        source
        @[reducible, inline]
        abbrev NN.API.nn.models.mlp1OutShape (cfg : Mlp1Config) :
        Shape

        Output shape (batch × outDim) for an Mlp1Config.

        Instances For
          source
          def NN.API.nn.models.mlp1Relu (cfg : Mlp1Config) :
          M (Sequential (mlp1InShape cfg) (mlp1OutShape cfg))

          Build a single-hidden-layer MLP with ReLU activation:

          linear(inDim → hidDim) → relu → linear(hidDim → outDim).

          Instances For