disentangling-vae
Experiments for understanding disentanglement in VAE latent representations
- 843
- Python
- 4 y ago
Experiments for understanding disentanglement in VAE latent representations
Pytorch implementation of conditional Generative Adversarial Networks (cGAN) and conditional Deep Convolutional Generative Adversarial Networks (cDCGAN) for MNIST dataset
Pytorch implementation of Generative Adversarial Networks (GAN) and Deep Convolutional Generative Adversarial Networks (DCGAN) for MNIST and CelebA datasets
MSG-GAN: Multi-Scale Gradients GAN (Architecture inspired from ProGAN but doesn't use layer-wise growing)
PyTorch implementation of Conditional Deep Convolutional Generative Adversarial Networks (cDCGAN)
Apply Thatcher illusion on a set of face photos
PyTorch implemented generative models for CelebA dataset: DCGAN, LSGAN, WGAN, WGANGP, InfoGAN, BEGAN, VAE, VAEGAN
DDPM, classifier-free guidance, and DDIM written from scratch in PyTorch · 111 offline tests · MNIST CPU smoke run measured and reported honestly; CIFAR-10 and CelebA configs ship untrained