pixel-cnn

Generative model

A generative model with tractable likelihood and easy sampling, allowing for efficient data generation.

Code for the paper "PixelCNN++: A PixelCNN Implementation with Discretized Logistic Mixture Likelihood and Other Modifications"

GitHub

2k stars
226 watching
437 forks
Language: Python
last commit: almost 5 years ago
paper

Related projects:

Repository Description Stars
simonkohl/probabilistic_unet Reimplementation of a neural network model for conditional segmentation of ambiguous images 546
openai/finetune-transformer-lm This project provides code and model for improving language understanding through generative pre-training using a transformer-based architecture. 2,160
ahmedfgad/numpycnn An implementation of a convolutional neural network (CNN) using NumPy for basic classification tasks. 570
yunishi3/3d-fcr-alphagan This project aims to develop a generative model for 3D multi-object scenes using a novel network architecture inspired by auto-encoding and generative adversarial networks. 103
preritj/segmentation Deep learning models for semantic segmentation of images 100
benedekrozemberczki/mixhop-and-n-gcn A deep learning framework implementation of higher-order graph convolutional architectures and their applications 402
zfturbo/keras-mask-rcnn-for-open-images-2019-instance-segmentation Provides pre-trained Mask R-CNN models and example code for instance segmentation on the Open Images Dataset 56
google-deepmind/recurrentgemma An implementation of a fast and efficient language model architecture 607
ecobost/cnn4brca This project uses Convolutional Neural Networks (CNN) for image segmentation of breast cancer lesions. 75
hongyanggao/pixeltcn An implementation of a custom convolutional neural network layer designed to improve up-sampling operations in deep learning models 97
ahmedfgad/cnngenetic Trains convolutional neural networks using the genetic algorithm 22
nv-tlabs/gscnn This code implements a neural network architecture designed to perform semantic segmentation in computer vision tasks. 920
conan7882/googlenet-inception An implementation of a deep neural network architecture for image classification using pre-trained models and fine-tuning on the CIFAR-10 dataset. 282
codeplea/genann A minimal C library for training and using feedforward artificial neural networks 2,010
gwgundersen/dpcca Develops a method to learn shared latent structure between biomedical images and gene expression data 25