hvae_gen

→VAEForImageGeneration

hvae_gen(pretrained: bool = False, overrides: object = {})

source edit

Construct a hierarchical VAE with the ELBO loss and prior-sample .generate().

Same trunk as hvae (3-level latent stack, 3-stage encoder), wrapped with the hierarchical ELBO training loss (reconstruction + sum of per-level $\beta$ -weighted KLs) and a convenience prior sampler that draws one $z_l \sim \mathcal{N}(0, \mathbf{I})$ per level.

Model Size

Parameters

pretrainedbool= False

Reserved for future weight registration; currently a no-op.

**overridesobject= {}

Optional VAEConfig field overrides forwarded into the underlying config.

Returns

VAEForImageGeneration

Hierarchical VAE wrapped with ELBO loss and prior sampler.

Notes

Reference: Sønderby, Raiko, Maaløe, Sønderby, and Winther, "Ladder Variational Autoencoders", NeurIPS, 2016 (arXiv:1602.02282).

Examples

>>> import lucid
>>> from lucid.models.generative.vae import hvae_gen
>>> model = hvae_gen().eval()
>>> x = lucid.randn((1, 3, 32, 32))
>>> out = model(x)
>>> out.sample.shape, out.kl_loss.shape
((1, 3, 32, 32), ())

Used by 1

lucid.models.generative.vae

>>> import lucid >>> from lucid.models.generative.vae import hvae_gen >>> model = hvae_gen().eval() >>> x = lucid.randn((1, 3, 32, 32)) >>> out = model(x) >>> out.sample.shape, out.kl_loss.shape ((1, 3, 32, 32), ())