realnvp_imagenet64_gen(pretrained: bool = False, overrides: object = {})RealNVP generator for Imagenet 64 x 64.
Same bijection as realnvp_imagenet64, wrapped with the
bits/dim objective and the ancestral sampler.
Model Size
Parameters
pretrainedbool= FalseReserved for future weight registration; currently a no-op.
**overridesobject= {}Optional
RealNVPConfig field overrides forwarded into
the underlying config.Returns
RealNVPForImageGenerationGenerator configured with the Imagenet 64 x 64 setup.
Notes
Reference: Dinh, Sohl-Dickstein, and Bengio, "Density Estimation Using Real NVP", ICLR, 2017 (arXiv:1605.08803). Reported: 3.98 bits/dim.
Examples
>>> from lucid.models.generative.realnvp import realnvp_imagenet64_gen
>>> model = realnvp_imagenet64_gen().eval()
>>> model.generate(n_samples=1).samples.shape
(1, 3, 64, 64)