GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → kundan2510 → Pixelcnn

kundan2510 / Pixelcnn

Licence: mit
Theano reimplementation of pixelCNN architecture

Programming Languages

python
139335 projects - #7 most used programming language

Labels

deep-learningtheanoimage-generation

Projects that are alternatives of or similar to Pixelcnn

Nmtpy
nmtpy is a Python framework based on dl4mt-tutorial to experiment with Neural Machine Translation pipelines.
Stars: ✭ 127 (-25.29%)
Mutual labels:  theano
Ilqr
Iterative Linear Quadratic Regulator with auto-differentiatiable dynamics models
Stars: ✭ 141 (-17.06%)
Mutual labels:  theano
Mmediting
OpenMMLab Image and Video Editing Toolbox
Stars: ✭ 2,618 (+1440%)
Mutual labels:  image-generation
Oneshottranslation
Pytorch implementation of "One-Shot Unsupervised Cross Domain Translation" NIPS 2018
Stars: ✭ 135 (-20.59%)
Mutual labels:  image-generation
Focal Frequency Loss
Focal Frequency Loss for Generative Models
Stars: ✭ 141 (-17.06%)
Mutual labels:  image-generation
Livianet
This repository contains the code of LiviaNET, a 3D fully convolutional neural network that was employed in our work: "3D fully convolutional networks for subcortical segmentation in MRI: A large-scale study"
Stars: ✭ 143 (-15.88%)
Mutual labels:  theano
Cyclegan
Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.
Stars: ✭ 10,933 (+6331.18%)
Mutual labels:  image-generation
Neuralnets
Deep Learning libraries tested on images and time series
Stars: ✭ 163 (-4.12%)
Mutual labels:  theano
Tsit
[ECCV 2020 Spotlight] A Simple and Versatile Framework for Image-to-Image Translation
Stars: ✭ 141 (-17.06%)
Mutual labels:  image-generation
Vae Lagging Encoder
PyTorch implementation of "Lagging Inference Networks and Posterior Collapse in Variational Autoencoders" (ICLR 2019)
Stars: ✭ 153 (-10%)
Mutual labels:  image-generation
Gesturegan
[ACM MM 2018 Oral] GestureGAN for Hand Gesture-to-Gesture Translation in the Wild
Stars: ✭ 136 (-20%)
Mutual labels:  image-generation
Unetgan
Official Implementation of the paper "A U-Net Based Discriminator for Generative Adversarial Networks" (CVPR 2020)
Stars: ✭ 139 (-18.24%)
Mutual labels:  image-generation
Aesara
Aesara is a fork of the Theano library that is maintained by the PyMC developers. It was previously named Theano-PyMC.
Stars: ✭ 145 (-14.71%)
Mutual labels:  theano
Ganspapercollection
Stars: ✭ 130 (-23.53%)
Mutual labels:  theano
Scene generation
A PyTorch implementation of the paper: Specifying Object Attributes and Relations in Interactive Scene Generation
Stars: ✭ 158 (-7.06%)
Mutual labels:  image-generation
Handwritten Digit Recognition Using Deep Learning
Handwritten Digit Recognition using Machine Learning and Deep Learning
Stars: ✭ 127 (-25.29%)
Mutual labels:  theano
Real Time Ml Project
A curated list of applied machine learning and data science notebooks and libraries across different industries.
Stars: ✭ 143 (-15.88%)
Mutual labels:  theano
Tilegan
Code for TileGAN: Synthesis of Large-Scale Non-Homogeneous Textures (SIGGRAPH 2019)
Stars: ✭ 166 (-2.35%)
Mutual labels:  image-generation
Deep Svdd
Repository for the Deep One-Class Classification ICML 2018 paper
Stars: ✭ 159 (-6.47%)
Mutual labels:  theano
Mariana
The Cutest Deep Learning Framework which is also a wonderful Declarative Language
Stars: ✭ 151 (-11.18%)
Mutual labels:  theano
View All Similar Projects ➔

Generating images pixel by pixel

Theano implementation of pixelCNN architecture

This repository contains code for training an image generator using a slight variant of the pixelCNN architecture as described in Conditional Image Generation with PixelCNN Decoders

Most of the code is in core theano. 'keras' has been used for loading data. Optimizer implementation from 'lasagne' has been used.

Dependencies:

theano

lasagne

keras

You can use experiments.sh to train the model and install_dependencies.sh to install the dependencies.

Notes on results:

  1. Images with 2-bit depth has been considered for training as well as generation e.g. every pixel is quantized into four levels and then used for training. Four-way softmax has been used to predict pixel quantization.

  2. Following is the result after 60 epochs of training which got completed in about 10 hrs on K6000 Gpu. No hyper parameter search has been performed.

Generated images

Generated images

Training images

Training images

Salient features: No blind spots, efficient implemenattion of vertical stacks and horizontal stacks, residual connections and good generation results :D

For any comments/feedback, feel free to email me at [email protected] or open an issue here.

TODO: Implement gated activation and conditional generation.

If you have GPU resources, feel free to train on CIFAR10. I have provided training script for that. Let me know how it goes. Also, one can train with 256-way softmax and perform hyperparameter search on MNIST dataset.

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].