micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)、Low-Bit(≤2b)/Ternary and Binary(TWN/BNN/XNOR-Net); post-training-quantization(PTQ), 8-bit(tensorrt); 2、 pruning: normal、reg…

A toolbox for spectral compressive imaging reconstruction including MST (CVPR 2022), CST (ECCV 2022), DAUHST (NeurIPS 2022), BiSCI (NeurIPS 2023), HDNet (CVPR 2022), MST++ (CVPRW 2022), etc.

PyTorch-based library for Riemannian Manifold Hamiltonian Monte Carlo (RMHMC) and inference in Bayesian neural networks

Highly optimized inference engine for Binarized Neural Networks

This project is the official implementation of 'Basic Binary Convolution Unit for Binarized Image Restoration Network', ICLR2023

Bayesian Neural Network in PyTorch

The collection of training tricks of binarized neural networks.

A Toolbox for Binarized Spectral Compressive Imaging (NeurIPS 2023)

System Verilog code describing a fully combinational binarized neural network.

[ICCV 2021] Code release for "Sub-bit Neural Networks: Learning to Compress and Accelerate Binary Neural Networks"

A PyTorch implemenation of real XNOR-popcount (1-bit op) GEMM Linear PyTorch extension support both CPU and CUDA

HLS code for a BNN accelerator

Optimization of Transmit Beamforming based on Unsupervised Learning With Channel Covariances for MISO Downlink Assisted by Reconfigurable Intelligent Surfaces

Towards Accurate Binary Neural Networks via Modeling Contextual Dependencies

This project aims to integrate Domain Knowledge with Bayesian Deep Learning through an intuitive Active Learning interface

Awesome papers on Neural Networks and Deep Learning

This is a framework for binary neural network based mmclassification

Neural Property Approximate Quantifier

Repo for my thesis research development at UC Riverside: "Classifying Galaxy Morphologies Using Bayesian Neural Networks for LSST"

Bayesian Neural Networks with Parallelized Sampling of LogLikelihood