Displaying 1 to 20 from 24 results

generative-models - Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.

  •    Python

Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow. Also present here are RBM and Helmholtz Machine. Generated samples will be stored in GAN/{gan_model}/out (or VAE/{vae_model}/out, etc) directory during training.

TensorFlow-VAE-GAN-DRAW - A collection of generative methods implemented with TensorFlow (Deep Convolutional Generative Adversarial Networks (DCGAN), Variational Autoencoder (VAE) and DRAW: A Recurrent Neural Network For Image Generation)

  •    Python

TensorFlow implementation of Deep Convolutional Generative Adversarial Networks, Variational Autoencoder (also Deep and Convolutional) and DRAW: A Recurrent Neural Network For Image Generation. Deep Convolutional Generative Adversarial Networks produce decent results after 10 epochs using default parameters.

vae-style-transfer - An experiment in VAE-based artistic style transfer by embedding fiddling.

  •    Python

The project was created as part of the Creative Applications of Deep Learning with TensorFlow (CADL) Kadenze course's final assignment. It is an experimental attempt to transfer artistic style learned from a series of paintings "live" onto a video sequence by fitting a variational autoencoder with 512 codes to both paintings and video frames, isolating the mean feature-space embeddings and modifying the video's embeddings to be closer to those of the paintings. Because the general visual quality of the VAE's decoded output is relatively low, a convolutional post-processing network based on residual convolutions was trained with the purpose of making the resulting image less similar to the VAE's generated output and more similar to the original input images. The basic idea was to have an upsampling network here, but it quickly turned out to be a very naive idea at this point of development. Instead, it now downsizes the input, learns filters in a residual network and then samples back up to the input frame size; I would have liked to perform convolutions directly on the input, but memory limitations prevented the usage of a useful amount of feature maps.

vae-seq - Variational Auto-Encoders in a Sequential Setting.

  •    Python

VAE-Seq is a library for modeling sequences of observations. One tool that's commonly used to model sequential data is the Recurrent Neural Network (RNN), or gated variations of it such as the Long Short-Term Memory cell or the Gated Recurrent Unit cell.

joint_vae - Code to build VAE models that are jointly conditioned.

  •    OpenEdge

Vedantam, Ramakrishna, Ian Fischer, Jonathan Huang, and Kevin Murphy. 2017. Generative Models of Visually Grounded Imagination. arXiv [cs.LG]. arXiv. http://arxiv.org/abs/1705.10762. NOTE: All scripts should be run from the root directory of the project.

variational-autoencoder-theano - Variational Autoencoders (VAEs) in Theano for Images and Text

  •    Python

Variational Autoencoders (VAEs) in Theano for Images and Text

video_prediction - Stochastic Adversarial Video Prediction

  •    Python

TensorFlow implementation for stochastic adversarial video prediction. Given a sequence of initial frames, our model is able to predict future frames of various possible futures. For example, in the next two sequences, we show the ground truth sequence on the left and random predictions of our model on the right. Predicted frames are indicated by the yellow bar at the bottom. For more examples, visit the project page. Stochastic Adversarial Video Prediction, Alex X. Lee, Richard Zhang, Frederik Ebert, Pieter Abbeel, Chelsea Finn, Sergey Levine. arXiv preprint arXiv:1804.01523, 2018.

dsprites-dataset - Dataset to assess the disentanglement properties of unsupervised learning methods

  •    Jupyter

This repository contains the dSprites dataset, used to assess the disentanglement properties of unsupervised learning methods. dSprites is a dataset of 2D shapes procedurally generated from 6 ground truth independent latent factors. These factors are color, shape, scale, rotation, x and y positions of a sprite.


  •    Python

This repository contains implementation of VAE and beta-VAE. Following are the generated samples after 82000 iterations of training on celeb-A dataset.

attend_infer_repeat - A Tensorfflow implementation of Attend, Infer, Repeat

  •    Python

This is an unofficial Tensorflow implementation of Attend, Infear, Repeat (AIR), as presented in the following paper: S. M. Ali Eslami et. al., Attend, Infer, Repeat: Fast Scene Understanding with Generative Models. I describe the implementation and the issues I run into while working on it in this blog post.

sqair - Implementation of Sequential Attend, Infer, Repeat (SQAIR)

  •    Jupyter

This is an official Tensorflow implementation of Sequential Attend, Infer, Repeat (SQAIR), as presented in the following paper: A. R. Kosiorek, H. Kim, I. Posner, Y. W. Teh, Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects. SQAIR learns to reconstruct a sequence of images by detecting objects in every frame and then propagating them to the following frames. This results in unsupervised object detection & tracking, which we can see in the figure below. The figure was generated from a model trained for 1M iterations. The maximum number of objects in a frame (and therefore number of detected and propagated objects) is set to four, but there are never more than two objects. The first row shows inputs to the model (time flies from left to right), while the second row shows reconstructions with marked glimpse locations. Colors of the bounding boxes correspond to object id. Here, the color is always the same, which means that objects are properly tracked.

VAE-Gumbel-Softmax - An implementation of a Variational-Autoencoder using the Gumbel-Softmax reparametrization trick in TensorFlow (tested on r1

  •    Python

Also, included is a jupyter notebook which shows how the Gumbel-Max trick for sampling discrete variables relates to Concrete distributions. Note: Current Dockerfile is for TensorFlow 1.5 CPU training.

tf-vqvae - Tensorflow Implementation of the paper [Neural Discrete Representation Learning](https://arxiv

  •    Jupyter

This repository implements the paper, Neural Discrete Representation Learning (VQ-VAE) in Tensorflow. ⚠️ This is not an official implementation, and might have some glitch (,or a major defect).

beat-blender - Blend beats using machine learning to create music in a fun new way.

  •    Javascript

Built using deeplearn.js and MusicVAE. Beat Blender requires the GCloud SDK for running the server and node + npm for javascript development.

We have large collection of open source products. Follow the tags from Tag Cloud >>

Open source products are scattered around the web. Please provide information about the open source projects you own / you use. Add Projects.