kundan2510/pixelCNN
Theano reimplementation of pixelCNN architecture
This project offers a deep learning tool for developers to train models that generate new images, pixel by pixel. It takes a dataset of existing images and learns to produce novel images that resemble the training data. This is useful for machine learning engineers or researchers working on generative models and image synthesis.
166 stars. No commits in the last 6 months.
Use this if you are a deep learning practitioner interested in exploring or implementing the PixelCNN architecture for image generation tasks.
Not ideal if you are looking for a high-level, production-ready image generation tool that doesn't require direct interaction with deep learning frameworks like Theano.
Stars
166
Forks
34
Language
Python
License
MIT
Category
Last pushed
Jul 23, 2016
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/kundan2510/pixelCNN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
zhangqianhui/Conditional-GAN
Tensorflow implementation for Conditional Convolutional Adversarial Networks.
mit-han-lab/data-efficient-gans
[NeurIPS 2020] Differentiable Augmentation for Data-Efficient GAN Training
EugenHotaj/pytorch-generative
Easy generative modeling in PyTorch
shaohua0116/DCGAN-Tensorflow
A Tensorflow implementation of Deep Convolutional Generative Adversarial Networks trained on...
pytti-tools/pytti-notebook
Start here