XingyuXie

Adan

Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models

EditAnything

Edit anything in images powered by segment-anything, ControlNet, StableDiffusion, etc. (ACM MM)

BMTrain-Adan

Efficient Training (including pre-training and fine-tuning) for Big Models

CNN-FaceKeyPoint-Detection

FaceKeyPoint Detection using CNN

D-LADMM

Differentiable Linearized ADMM (to appear in ICML 2019)

IBDLR

Implicit Block Diagonal Low-Rank Representation

Matrix-recovery-with-implicitly-low-rank-data

The code for the paper "Matrix recovery with implicitly low-rank data"

Maximum-and-Concatenation-Networks

Code for the ICML 2020 Paper ''Maximum-and-Concatenation Networks''

notes

研究生阶段的一些文章（技术、思考、读书笔记、日常琐事等）

The-Augmented-Lagrange-Multiplier-Method

The Augmented Lagrange Multiplier Method for min{A,S} ||X - ASY ||_F^2 + alpha ||Y||_F^2

XingyuXie/Matrix-recovery-with-implicitly-low-rank-data

The code for the paper "Matrix recovery with implicitly low-rank data"

XingyuXie/IBDLR

Implicit Block Diagonal Low-Rank Representation

XingyuXie/Maximum-and-Concatenation-Networks

Code for the ICML 2020 Paper ''Maximum-and-Concatenation Networks''

XingyuXie/BMTrain-Adan

Efficient Training (including pre-training and fine-tuning) for Big Models

XingyuXie/D-LADMM

Differentiable Linearized ADMM (to appear in ICML 2019)

XingyuXie/notes

研究生阶段的一些文章（技术、思考、读书笔记、日常琐事等）

XingyuXie/ConvNeXt

Code release for ConvNeXt model

XingyuXie/Deep-Kernel-GP

Deep Kernel Learning. Gaussian Process Regression where the input is a neural network mapping of x that maximizes the marginal likelihood

XingyuXie/Deep-subspace-clustering-networks

XingyuXie/deit

Official DeiT repository

XingyuXie/faceswap

Deepfakes Software For All

XingyuXie/fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

XingyuXie/jittor

Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.

XingyuXie/learn2branch

Exact Combinatorial Optimization with Graph Convolutional Neural Networks (NeurIPS 2019)

XingyuXie/Low-rank-kernel-subspace-clustering

XingyuXie/mae

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

XingyuXie/Megatron-DeepSpeed

Ongoing research training transformer language models at scale, including: BERT & GPT-2

XingyuXie/Megatron-LM

Ongoing research training transformer models at scale

XingyuXie/Metrics

Machine learning evaluation metrics, implemented in Python, R, Haskell, and MATLAB / Octave

XingyuXie/mmclassification

OpenMMLab Image Classification Toolbox and Benchmark

XingyuXie/MobileNet-SSD

Caffe implementation of Google MobileNet SSD detection network, with pretrained weights on VOC0712 and mAP=0.727.

XingyuXie/MoEP-RSS

Robust Low-Rank Subspace Segmentation with Finite Mixture Noise

XingyuXie/mugs

A PyTorch implementation of Mugs proposed by our paper "Mugs: A Multi-Granular Self-Supervised Learning Framework".

XingyuXie/multibranch

Codes for the paper "Deep Neural Networks with Multi-Branch Architectures Are Less Non-Convex"

XingyuXie/NMS

XingyuXie/PKUAutoSubmit

PKU一键出入校备案小工具

XingyuXie/poolformer

PoolFormer: MetaFormer Is Actually What You Need for Vision (CVPR 2022 Oral)

XingyuXie/pytorch_velo

VeLO optimizer in PyTorch

XingyuXie/TinyLlama

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

XingyuXie/transformer-xl