kvmanohar22 / Generative Models
Comparison of Generative Models in Tensorflow
Stars: ✭ 96
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Generative Models
Tensorflow Generative Model Collections
Collection of generative models in Tensorflow
Stars: ✭ 3,785 (+3842.71%)
Mutual labels: gan, mnist, vae
Pytorch Rl
This repository contains model-free deep reinforcement learning algorithms implemented in Pytorch
Stars: ✭ 394 (+310.42%)
Mutual labels: gan, vae
Pytorch Mnist Celeba Gan Dcgan
Pytorch implementation of Generative Adversarial Networks (GAN) and Deep Convolutional Generative Adversarial Networks (DCGAN) for MNIST and CelebA datasets
Stars: ✭ 363 (+278.13%)
Mutual labels: gan, mnist
Generative Models
Annotated, understandable, and visually interpretable PyTorch implementations of: VAE, BIRVAE, NSGAN, MMGAN, WGAN, WGANGP, LSGAN, DRAGAN, BEGAN, RaGAN, InfoGAN, fGAN, FisherGAN
Stars: ✭ 438 (+356.25%)
Mutual labels: gan, vae
Fashion Mnist
A MNIST-like fashion product database. Benchmark 👇
Stars: ✭ 9,675 (+9978.13%)
Mutual labels: gan, mnist
Pycadl
Python package with source code from the course "Creative Applications of Deep Learning w/ TensorFlow"
Stars: ✭ 356 (+270.83%)
Mutual labels: gan, vae
Tensorflow Mnist Vae
Tensorflow implementation of variational auto-encoder for MNIST
Stars: ✭ 422 (+339.58%)
Mutual labels: mnist, vae
Fun-with-MNIST
Playing with MNIST. Machine Learning. Generative Models.
Stars: ✭ 23 (-76.04%)
Mutual labels: mnist, vae
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).
Stars: ✭ 577 (+501.04%)
Mutual labels: gan, vae
Generative Models
Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.
Stars: ✭ 6,701 (+6880.21%)
Mutual labels: gan, vae
Advanced Deep Learning With Keras
Advanced Deep Learning with Keras, published by Packt
Stars: ✭ 917 (+855.21%)
Mutual labels: gan, vae
MNIST-invert-color
Invert the color of MNIST images with PyTorch
Stars: ✭ 13 (-86.46%)
Mutual labels: gan, mnist
VAE-Gumbel-Softmax
An implementation of a Variational-Autoencoder using the Gumbel-Softmax reparametrization trick in TensorFlow (tested on r1.5 CPU and GPU) in ICLR 2017.
Stars: ✭ 66 (-31.25%)
Mutual labels: mnist, vae
tensorflow-mnist-AAE
Tensorflow implementation of adversarial auto-encoder for MNIST
Stars: ✭ 86 (-10.42%)
Mutual labels: mnist, vae
Relativistic Average Gan Keras
The implementation of Relativistic average GAN with Keras
Stars: ✭ 36 (-62.5%)
Mutual labels: gan, mnist
Disentangling Vae
Experiments for understanding disentanglement in VAE latent representations
Stars: ✭ 398 (+314.58%)
Mutual labels: mnist, vae
Gan Tutorial
Simple Implementation of many GAN models with PyTorch.
Stars: ✭ 227 (+136.46%)
Mutual labels: gan, mnist
Video prediction
Stochastic Adversarial Video Prediction
Stars: ✭ 247 (+157.29%)
Mutual labels: gan, vae
Rgan
Recurrent (conditional) generative adversarial networks for generating real-valued time series data.
Stars: ✭ 480 (+400%)
Mutual labels: gan, mnist
Comparison of Generative Models in Tensorflow
The different generative models considered here are Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs).
This experiment is accompanied by blog post at : https://kvmanohar22.github.io/Generative-Models
Usage
- Download the MNIST and CIFAR datasets
Train VAE on mnist by running:
python main.py --train --model vae --dataset mnist
Train GAN on mnist by running:
python main.py --train --model gan --dataset mnist
For the complete list of command line options, run:
python main.py --help
The model generates images at a frequence specified by generate_frq
which is by default 1.
Results of training GAN on mnist
Sample images from MNIST data is :
On the left is image generated from VAE and on the right is GIF showing images generated from GAN as a function of epochs:
For examples and explanation, have a look at the blog post.
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].