Uses of Record Class
ai.beestream.jitnn.nn.models.Vae.Output
Packages that use Vae.Output
Package
Description
Complete models: ResNet, MobileNetV2, GPT-2, a Llama-style decoder, BERT, a VAE, DCGAN, U-Net and
character RNNs, and the embedding models word2vec, doc2vec and GloVe.
-
Uses of Vae.Output in ai.beestream.jitnn.nn.models
Methods in ai.beestream.jitnn.nn.models that return Vae.OutputModifier and TypeMethodDescriptionEncodes x [B, in], samples z = mu + exp(logvar / 2) eps with the given noise eps [B, latent], decodes.Methods in ai.beestream.jitnn.nn.models with parameters of type Vae.OutputModifier and TypeMethodDescriptionstatic TensorVae.loss(Vae.Output o, Tensor x) The negative ELBO per sample: (binary cross-entropy summed over pixels + KL) / B.