TorchLean API

Docs HomeGuideExamplesGraphs

NN.Examples.Models.Generative.Vae

β-VAE-Style CIFAR Example #

Runnable compact VAE path over flattened CIFAR images.

The formal VAE objective and decomposition theorems live in NN.Spec.Models.Vae and NN.MLTheory.Generative.Latent.VAE. This executable uses a small supervised runtime target: reconstruct the image while keeping latent mean/log-variance proxy channels near zero.

source
def NN.Examples.Models.Generative.Vae.exeName :
String
Instances For
    source
    def NN.Examples.Models.Generative.Vae.defaultLogJson :
    System.FilePath
    Instances For
      source
      def NN.Examples.Models.Generative.Vae.cfg :
      API.nn.models.VectorGenerativeConfig
      Instances For
        source
        @[reducible, inline]
        abbrev NN.Examples.Models.Generative.Vae.σ :
        Shape
        Instances For
          source
          @[reducible, inline]
          abbrev NN.Examples.Models.Generative.Vae.τ :
          Shape
          Instances For
            source
            def NN.Examples.Models.Generative.Vae.mkModel :
            API.nn.M (API.nn.Sequential σ τ)
            Instances For
              source
              def NN.Examples.Models.Generative.Vae.main (args : List String) :
              IO UInt32
              Instances For