miyosuda / Disentangled_vae
Licence: other
Replicating "Understanding disentangling in β-VAE"
Stars: ✭ 188
Programming Languages
python
139335 projects - #7 most used programming language
Labels
Projects that are alternatives of or similar to Disentangled vae
Mojitalk
Code for "MojiTalk: Generating Emotional Responses at Scale" https://arxiv.org/abs/1711.04090
Stars: ✭ 107 (-43.09%)
Mutual labels: vae
Vmf vae nlp
Code for EMNLP18 paper "Spherical Latent Spaces for Stable Variational Autoencoders"
Stars: ✭ 140 (-25.53%)
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 (-18.62%)
Mutual labels: vae
Pytorch cpp
Deep Learning sample programs using PyTorch in C++
Stars: ✭ 114 (-39.36%)
Mutual labels: vae
Deep Learning With Python
Example projects I completed to understand Deep Learning techniques with Tensorflow. Please note that I do no longer maintain this repository.
Stars: ✭ 134 (-28.72%)
Mutual labels: vae
Beat Blender
Blend beats using machine learning to create music in a fun new way.
Stars: ✭ 147 (-21.81%)
Mutual labels: vae
Smrt
Handle class imbalance intelligently by using variational auto-encoders to generate synthetic observations of your minority class.
Stars: ✭ 102 (-45.74%)
Mutual labels: vae
Pytorch Vae
A CNN Variational Autoencoder (CNN-VAE) implemented in PyTorch
Stars: ✭ 181 (-3.72%)
Mutual labels: vae
Tensorflow Mnist Cvae
Tensorflow implementation of conditional variational auto-encoder for MNIST
Stars: ✭ 139 (-26.06%)
Mutual labels: vae
Vae Lagging Encoder
PyTorch implementation of "Lagging Inference Networks and Posterior Collapse in Variational Autoencoders" (ICLR 2019)
Stars: ✭ 153 (-18.62%)
Mutual labels: vae
O Gan
O-GAN: Extremely Concise Approach for Auto-Encoding Generative Adversarial Networks
Stars: ✭ 117 (-37.77%)
Mutual labels: vae
Srl Zoo
State Representation Learning (SRL) zoo with PyTorch - Part of S-RL Toolbox
Stars: ✭ 125 (-33.51%)
Mutual labels: vae
Pytorch Vae
A Collection of Variational Autoencoders (VAE) in PyTorch.
Stars: ✭ 2,704 (+1338.3%)
Mutual labels: vae
Factorvae
Pytorch implementation of FactorVAE proposed in Disentangling by Factorising(http://arxiv.org/abs/1802.05983)
Stars: ✭ 176 (-6.38%)
Mutual labels: vae
Cross Lingual Voice Cloning
Tacotron 2 - PyTorch implementation with faster-than-realtime inference modified to enable cross lingual voice cloning.
Stars: ✭ 106 (-43.62%)
Mutual labels: vae
Adversarial video summary
Unofficial PyTorch Implementation of SUM-GAN from "Unsupervised Video Summarization with Adversarial LSTM Networks" (CVPR 2017)
Stars: ✭ 187 (-0.53%)
Mutual labels: vae
Optimus
Optimus: the first large-scale pre-trained VAE language model
Stars: ✭ 180 (-4.26%)
Mutual labels: vae
Disentangled VAE
Replicating DeepMind's papers "β-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework" and "Understanding disentangling in β-VAE"
2D shape disentaglement
Result by changing latent Z from -3.0 to 3.0 with γ=100.0 and C=20.0
Latent variables with small variances seem extracting "x", "y", "rotation" and "scale" parameters.
(This experiment is using DeepMind's dsprite data set.)
Z | Image | Parameter | Variance |
---|---|---|---|
z0 | 0.9216 | ||
z1 | 0.9216 | ||
z2 | Rotation | 0.0011 | |
z3 | Rotation? | 0.0038 | |
z4 | Pos X | 0.0002 | |
z5 | 0.9384 | ||
z6 | Scale? | 0.0004 | |
z7 | 0.8991 | ||
z8 | 0.9483 | ||
z9 | Pos Y | 0.0004 |
Reconstruction result
Left: original Right: reconstructed image
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].