mandt-lab / vbq
Official code for ICML 2020 paper "Variational Bayesian Quantization"
☆23Updated 2 years ago
Alternatives and similar repositories for vbq:
Users that are interested in vbq are comparing it to the libraries listed below
- [ICML'21 Oral] Improving Lossless Compression Rates via Monte Carlo Bits-Back Coding☆14Updated 3 years ago
- Compression with Flows via Local Bits-Back Coding☆39Updated 5 years ago
- Code release for Hoogeboom, Emiel, Jorn WT Peters, Rianne van den Berg, and Max Welling. "Integer Discrete Flows and Lossless Compression…☆97Updated 5 years ago
- ☆35Updated 4 years ago
- ☆16Updated 2 years ago
- ☆145Updated 2 years ago
- This repository contains the code for our recent paper `Minimal Random Code Learning: Getting Bits Back from Compressed Model Parameters'☆21Updated 6 years ago
- Perceptual quality metrics for TensorFlow☆42Updated 2 years ago
- Compression tools for machine learning researchers☆84Updated last year
- Evaluating Lossy Compression Rates of Deep Generative Models☆14Updated 4 years ago
- Code to accompany the paper "Hierarchical Quantized Autoencoders"☆37Updated last year
- A TensorFlow implementation of perceptual generative autoencoder (PGA).☆23Updated 4 years ago
- Lossless compression using Probabilistic Circuits☆16Updated 3 years ago
- ☆42Updated 5 years ago
- Code for UAI 2020 paper "Locally Masked Convolution for Autoregressive Models"☆77Updated 4 years ago
- Official code repo for NeurIPS 2020 paper "Improving Inference for Neural Image Compression"☆49Updated last year
- Code for "Modeling Sparse Deviations for Compressed Sensing using Generative Models", ICML 2018☆24Updated 6 years ago
- Deep generative models for distribution-preserving lossy compression☆33Updated 6 years ago
- Low-variance, efficient and unbiased gradient estimation for optimizing models with binary latent variables. (ICLR 2019)☆28Updated 6 years ago
- Code for paper "Closing the Dequantization Gap: PixelCNN as a Single-Layer Flow"☆19Updated 4 years ago
- Estimating Gradients for Discrete Random Variables by Sampling without Replacement☆40Updated 5 years ago
- ☆21Updated 5 years ago
- ☆32Updated 6 years ago
- Code for "Online Learned Continual Compression with Adaptive Quantization Modules"☆27Updated 4 years ago
- ☆17Updated 4 years ago
- Implementation of iterative inference in deep latent variable models☆43Updated 5 years ago
- ☆30Updated 4 years ago
- Code for the article "What if Neural Networks had SVDs?", to be presented as a spotlight paper at NeurIPS 2020.☆75Updated 9 months ago
- ICML 2019. Turn a pre-trained GAN model into a content-addressable model without retraining.☆22Updated 9 months ago
- ☆49Updated 4 years ago