1Konny / Factorvae
Licence: mit
Pytorch implementation of FactorVAE proposed in Disentangling by Factorising(http://arxiv.org/abs/1802.05983)
Stars: ✭ 176
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Factorvae
Beta Vae
Pytorch implementation of β-VAE
Stars: ✭ 326 (+85.23%)
Mutual labels: unsupervised-learning, vae, celeba
Disentangling Vae
Experiments for understanding disentanglement in VAE latent representations
Stars: ✭ 398 (+126.14%)
Mutual labels: unsupervised-learning, vae, celeba
ladder-vae-pytorch
Ladder Variational Autoencoders (LVAE) in PyTorch
Stars: ✭ 59 (-66.48%)
Mutual labels: vae, unsupervised-learning
VAENAR-TTS
PyTorch Implementation of VAENAR-TTS: Variational Auto-Encoder based Non-AutoRegressive Text-to-Speech Synthesis.
Stars: ✭ 66 (-62.5%)
Mutual labels: vae, unsupervised-learning
style-vae
Implementation of VAE and Style-GAN Architecture Achieving State of the Art Reconstruction
Stars: ✭ 25 (-85.8%)
Mutual labels: vae, celeba
srVAE
VAE with RealNVP prior and Super-Resolution VAE in PyTorch. Code release for https://arxiv.org/abs/2006.05218.
Stars: ✭ 56 (-68.18%)
Mutual labels: vae, unsupervised-learning
Pycadl
Python package with source code from the course "Creative Applications of Deep Learning w/ TensorFlow"
Stars: ✭ 356 (+102.27%)
Mutual labels: vae, celeba
Awesome Vaes
A curated list of awesome work on VAEs, disentanglement, representation learning, and generative models.
Stars: ✭ 418 (+137.5%)
Mutual labels: unsupervised-learning, vae
Variational Autoencoder
Variational autoencoder implemented in tensorflow and pytorch (including inverse autoregressive flow)
Stars: ✭ 807 (+358.52%)
Mutual labels: unsupervised-learning, vae
Beat Blender
Blend beats using machine learning to create music in a fun new way.
Stars: ✭ 147 (-16.48%)
Mutual labels: vae
Vae Lagging Encoder
PyTorch implementation of "Lagging Inference Networks and Posterior Collapse in Variational Autoencoders" (ICLR 2019)
Stars: ✭ 153 (-13.07%)
Mutual labels: vae
Pytorch Vae
A Collection of Variational Autoencoders (VAE) in PyTorch.
Stars: ✭ 2,704 (+1436.36%)
Mutual labels: vae
A Hierarchical Latent Structure For Variational Conversation Modeling
PyTorch Implementation of "A Hierarchical Latent Structure for Variational Conversation Modeling" (NAACL 2018 Oral)
Stars: ✭ 153 (-13.07%)
Mutual labels: vae
Lr Gan.pytorch
Pytorch code for our ICLR 2017 paper "Layered-Recursive GAN for image generation"
Stars: ✭ 145 (-17.61%)
Mutual labels: unsupervised-learning
Dynamics
A Compositional Object-Based Approach to Learning Physical Dynamics
Stars: ✭ 159 (-9.66%)
Mutual labels: unsupervised-learning
Spherical Text Embedding
[NeurIPS 2019] Spherical Text Embedding
Stars: ✭ 143 (-18.75%)
Mutual labels: unsupervised-learning
Flappy Es
Flappy Bird AI using Evolution Strategies
Stars: ✭ 140 (-20.45%)
Mutual labels: unsupervised-learning
Tensorflowprojects
Deep learning using tensorflow
Stars: ✭ 167 (-5.11%)
Mutual labels: unsupervised-learning
Remixautoml
R package for automation of machine learning, forecasting, feature engineering, model evaluation, model interpretation, data generation, and recommenders.
Stars: ✭ 159 (-9.66%)
Mutual labels: unsupervised-learning
FactorVAE
Pytorch implementation of FactorVAE proposed in Disentangling by Factorising, Kim et al.(http://arxiv.org/abs/1802.05983)
Dependencies
python 3.6.4
pytorch 0.4.0 (or check pytorch-0.3.1 branch for pytorch 0.3.1)
visdom
tqdm
Datasets
- 2D Shapes(dsprites) Dataset
sh scripts/prepare_data.sh dsprites
- 3D Chairs Dataset
sh scripts/prepare_data.sh 3DChairs
- CelebA Dataset(download)
# first download img_align_celeba.zip and put in data directory like below
└── data
└── img_align_celeba.zip
# then run scrip file
sh scripts/prepare_data.sh CelebA
then data directory structure will be like below
.
└── data
└── dsprites-dataset
└── dsprites_ndarray_co1sh3sc6or40x32y32_64x64.npz
├── 3DChairs
└── images
├── 1_xxx.png
├── 2_xxx.png
├── ...
├── CelebA
└── img_align_celeba
├── 000001.jpg
├── 000002.jpg
├── ...
└── 202599.jpg
└── ...
NOTE: I recommend to preprocess image files(e.g. resizing) BEFORE training and avoid preprocessing on-the-fly.
Usage
initialize visdom
python -m visdom.server
you can reproduce results below as follows
e.g.
sh scripts/run_celeba.sh $RUN_NAME
sh scripts/run_dsprites_gamma6p4.sh $RUN_NAME
sh scripts/run_dsprites_gamma10.sh $RUN_NAME
sh scripts/run_3dchairs.sh $RUN_NAME
or you can run your own experiments by setting parameters manually
e.g.
python main.py --name run_celeba --dataset celeba --gamma 6.4 --lr_VAE 1e-4 --lr_D 5e-5 --z_dim 10 ...
check training process on the visdom server
localhost:8097
Results - 2D Shapes(dsprites) Dataset
Reconstruction($\gamma$=6.4)
Latent Space Traverse($\gamma$=6.4)
Latent Space Traverse($\gamma$=10)
Results - CelebA Dataset
Reconstruction
Latent Space Traverse
Results - 3D Chairs Dataset
Reconstruction
Latent Space Traverse
Reference
- Disentangling by Factorising, Kim et al.(http://arxiv.org/abs/1802.05983)
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].