bhpfelix / Variational Autoencoder Pytorch
Variational Autoencoder implemented with PyTorch, Trained over CelebA Dataset
Stars: ✭ 137
Programming Languages
python
139335 projects - #7 most used programming language
Variational Autoencoder for face image generation in PyTorch
Variational Autoencoder for face image generation implemented with PyTorch, Trained over a combination of CelebA + FaceScrub + JAFFE datasets.
Based on Deep Feature Consistent Variational Autoencoder (https://arxiv.org/abs/1610.00291 | https://github.com/houxianxu/DFC-VAE)
TODO: Add DFC-VAE implementation
Pretrained model available at https://drive.google.com/open?id=0B4y-iigc5IzcTlJfYlJyaF9ndlU
Results
Original Faces vs. Reconstructed Faces:
Linear interpolation between two face images:
Vector arithmatic in latent space:
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].