bnn

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、regular and group convolutional channel pruning; 3、 group convolution structure; 4、batch-normalization fuse for quantization. deploy: tensorrt, fp32/fp16/int8(ptq-calibration)、op-adapt(upsample)、dynamic_shape

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

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

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

This is a framework for binary neural network based mmclassification

Awesome papers on Neural Networks and Deep Learning

Neural Property Approximate Quantifier

BNN-to-FPGA framework, written in VHDL and Python

The official repository for the paper LAB: Learnable Activation Binarizer for Binary Neural Networks.