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"
2k stars
224 watching
436 forks
Language: Python
last commit: over 5 years ago paper
Related projects:
| Repository | Description | Stars |
|---|---|---|
| | Reimplementation of a neural network model for conditional segmentation of ambiguous images | 548 |
| | This project provides code and model for improving language understanding through generative pre-training using a transformer-based architecture. | 2,167 |
| | A Python implementation of a Convolutional Neural Network from scratch using NumPy for building CNNs from scratch | 577 |
| | 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 |
| | Deep learning models for semantic segmentation of images | 101 |
| | A deep learning framework implementation of higher-order graph convolutional architectures and their applications | 403 |
| | Provides pre-trained Mask R-CNN models and example code for instance segmentation on the Open Images Dataset | 56 |
| | An implementation of a fast and efficient language model architecture | 613 |
| | This project uses CNNs to segment breast cancer lesions from medical images. | 75 |
| | An implementation of a custom convolutional neural network layer designed to improve up-sampling operations in deep learning models | 97 |
| | Trains CNNs using a genetic algorithm for classification problems where one class per sample is allowed. | 22 |
| | This code implements a neural network architecture designed to perform semantic segmentation in computer vision tasks. | 920 |
| | An implementation of a deep neural network architecture for image classification using pre-trained models and fine-tuning on the CIFAR-10 dataset. | 285 |
| | A minimal C library for training and using feedforward artificial neural networks | 2,017 |
| | Develops a method to learn shared latent structure between biomedical images and gene expression data | 25 |