JingyangXiang

MaxQ

Pytorch implementation of our paper MaxQ: Multi-Axis Query for N:M Sparsity Network accepted by CVPR 2024.

SUBP

Pytorch implementation of our paper SUBP: Soft Uniform Block Pruning for 1xN Sparse CNNs Multithreading Acceleration accepted by NeurIPS 2023.

OvSW

Pytorch implementation of our paper OvSW: Overcoming Silent Weights for Accurate Binary Neural Networks accepted by ECCV 2024.

PointCloud-Record

记录点云SemanticKITTI论文阅读记录

Neural-Network-Pruning-through-its-RegularGraph-Structure

Pytorch implementation of our paper RGP: Neural Network Pruning Through Regular Graph With Edges Swapping accepted by TNNLS.

ImgeNet_MindSpore_Pipline

paper_reading

paper_recording_2021

大四阶段的论文阅读记录

CR-SFP

jetson-inference

Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.

JingyangXiang.github.io

BiDet

This is the official pytorch implementation for paper: BiDet: An Efficient Binarized Object Detector, which is accepted by CVPR2020.

bolt-noah

Bolt is a deep learning library with high performance and heterogeneous flexibility.

cs-self-learning

计算机自学指南

d2l-mindspore

《动手学深度学习》的MindSpore实现。供MindSpore学习者配合李沐老师课程使用。

d2l-zh

《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被60多个国家的400多所大学用于教学。

Latex-Poster-Template

LaTex Poster for S3-NeRF (NeurIPS 2022)

FQ-ViT

[IJCAI 2022] FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer

LLM-QAT

Code repo for the paper "LLM-QAT Data-Free Quantization Aware Training for Large Language Models"

OmniQuant

[ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.

Optimization-on-Stiefel-Manifold-via-Cayley-Transform

Efficient Riemannian Optimization on Stiefel Manifold via Cayley Transform

QQQ

QQQ is an innovative and hardware-optimized W4A8 quantization solution.

SpinQuant

Code repo for the paper "SpinQuant LLM quantization with learned rotations"