Skip to content
master
Switch branches/tags
Code

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
Sep 30, 2019
Feb 20, 2018
Feb 20, 2018
Feb 20, 2018
Feb 20, 2018

Multi-View Data Generation Without View Supervision

An implementation of the models presented in the Multi-View Data Generation Without View Supervision by Mickael Chen, Ludovic Denoyer and Thierry Artières, ICLR 2018

gmv

We propose a generative models for multi-view data by decomposing the latent space between content and view.

Usage

The code runs using PyTorch and numpy.

Each file is a stand-alone for the training of one model.

python gmv.py

gmv and cgmv are proposed model. gan2 is a simple baseline described in the paper. mathieu is a pytorch reimplementation of Disentangling factors of variation in deep representations using adversarial training using DCGAN inspired architecture.

Hyperparameters are set within the code and can be modified.

About

An implementation using pytorch of the models presented in the Multi-View Data Generation Without View Supervision paper.

Resources

License

Releases

No releases published

Packages

No packages published

Languages