guoyong

LLM-Interview-Code. Python

AI-Interview-Code. LLM大模型（重点）以及搜广推等 AI 算法中手写的面试题，（非 LeetCode），比如 Self-Attention, AUC等，一般比 LeetCode 更考察一个人的综合能力，又更贴近业务和基础知识一点

HunyuanImage-3.0. HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation

LongLive. Long Video Gen Infrastructure

Wan2.2. Wan: Open and Advanced Large-Scale Video Generative Models

diffusion-4k. [CVPR 2025] Diffusion-4K: Ultra-High-Resolution Image Synthesis with Latent Diffusion Models

True-Story-of-Pangu. 诺亚盘古大模型研发背后的真正的心酸与黑暗的故事。

FlashVideo. [AAAI-2026]FlashVideo: Flowing Fidelity to Detail for Efficient High-Resolution Video Generation

fractalgen. PyTorch implementation of FractalGen https://arxiv.org/abs/2502.17437

GPD. Python

FluxSR.

flux. Official inference repo for FLUX.1 models

ControlNeXt. Controllable video and image Generation, SVD, Animate Anyone, ControlNet, ControlNeXt, LoRA

FeMaSR. PyTorch codes for "Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priors", ACM MM2022 (Oral)

sam2. The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

ai-hub-models. Qualcomm® AI Hub Models is our collection of state-of-the-art machine learning models optimized for performance (latency, memory etc.) and ready to deploy on Qualcomm® devices.

SeeSR. [CVPR2024] SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution

BK-SDM. A Compressed Stable Diffusion for Efficient Text-to-Image Generation [ECCV'24]

GFPGAN. GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

DiffIR. This project is the official implementation of 'Diffir: Efficient diffusion model for image restoration', ICCV2023

OSEDiff. [NeurlPS2024] One-Step Effective Diffusion Network for Real-World Image Super-Resolution

SinSR. [CVPR 2024] SinSR: Diffusion-Based Image Super-Resolution in a Single Step

2DQuant. PyTorch code for our paper "2DQuant: Low-bit Post-Training Quantization for Image Super-Resolution"

awesome-LLMs-In-China. 中国大模型

SUPIR. SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild. Our new online demo is also released at suppixel.ai.

temporal-robustness-benchmark. Python

pytorch-mobilenet-v1. Python

Open-Sora-Plan. This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

OREPA_CVPR2022. CVPR 2022 "Online Convolutional Re-parameterization"

mlx. MLX: An array framework for Apple silicon

DRC. Dual Regression Compression for SR Models

DCLS-SR. Official PyTorch implementation of the paper "Deep Constrained Least Squares for Blind Image Super-Resolution", CVPR 2022.

diffusers. 🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

generative-models. Generative Models by Stability AI

generators-with-stylegan2. Here is a series of face generators based on StyleGAN2

AutoEnterScript. AutoEnter#自动输入脚本软件The script implements the ability to read the contents of the file on the native machine and enter it automatically

HCD. Python

distill-sd. Segmind Distilled diffusion

qidk. C

TAPADL. Code of "Robustifying Token Attention for Vision Transformers"

RSPC. Code for "Improving Robustness of Vision Transformers by Reducing Sensitivity to Patch Corruptions"

AttCAT. codes for paper "AttCAT: Explaining Transformers via Attentive Class Activation Tokens"

vit-explain. Explainability for Vision Transformers

ccl. Python

Adan. Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models

vits-robustness-torch. Code for the paper "A Light Recipe to Train Robust Vision Transformers" [SaTML 2023]

DSM-NAS. PyTorch Implementation of "Efficient Neural Architecture Search via Dominative Subspace Mining".

EWS. Code for "Improving Robustness by Enhancing Weak Subnets"

MobileFormer. Code and models for mobile-former

robustness. A library for experimenting with, training and evaluating neural networks, with a focus on adversarial robustness.

on-the-adversarial-robustness-of-visual-transformer. Code for the paper "On the Adversarial Robustness of Visual Transformers"

MPViT. [CVPR 2022] MPViT:Multi-Path Vision Transformer for Dense Prediction

TokenLabeling. Pytorch implementation of "All Tokens Matter: Token Labeling for Training Better Vision Transformers"

FAN. Official PyTorch implementation of Fully Attentional Networks

PNAG. PNAG

Transformer-Explainability. [CVPR 2021] Official PyTorch implementation for Transformer Interpretability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks.

DynamicViT. [NeurIPS 2021] [T-PAMI] DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification

ConvNeXt. Code release for ConvNeXt model

pytorch-cnn-visualizations. Pytorch implementation of convolutional neural network visualization techniques

MAE-pytorch. Unofficial PyTorch implementation of Masked Autoencoders Are Scalable Vision Learners

CvT. This is an official implementation of CvT: Introducing Convolutions to Vision Transformers.

Robust-Vision-Transformer. The implementation of our paper: Towards Robust Vision Transformer (CVPR2022)

semisup-adv. Semisupervised learning for adversarial robustness https://arxiv.org/pdf/1905.13736.pdf

convmixer. Implementation of ConvMixer for "Patches Are All You Need? 🤷"

Bag-of-Tricks-for-AT. Empirical tricks for training robust models (ICLR 2021)

robust_overfitting. Python

robustbench. RobustBench: a standardized adversarial robustness benchmark [NeurIPS 2021 Benchmarks and Datasets Track]

auto-attack. Code relative to "Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks"

Image-Super-Resolution-via-Iterative-Refinement. Unofficial implementation of Image Super-Resolution via Iterative Refinement by Pytorch

deepmind-research. This repository contains implementations and illustrative code to accompany DeepMind publications

MART. Code for ICLR2020 "Improving Adversarial Robustness Requires Revisiting Misclassified Examples"

TRADES. TRADES (TRadeoff-inspired Adversarial DEfense via Surrogate-loss minimization)

RSLAD. This is the official code for "Revisiting Adversarial Robustness Distillation: Robust Soft Labels Make Student Better"

RobNets. [CVPR 2020] When NAS Meets Robustness: In Search of Robust Architectures against Adversarial Attacks

simple-blackbox-attack. Code for ICML 2019 paper "Simple Black-box Adversarial Attacks"

ConvNorm. Official Implementation of Convolutional Normalization: Improving Robustness and Training for Deep Neural Networks

RobustArchitectureSearch. This github repository contains the official code for the paper, "Evolving Robust Neural Architectures to Defend from Adversarial Attacks"

pytorch-lr-dropout. "Learning Rate Dropout" in PyTorch

DiverseBranchBlock. Diverse Branch Block: Building a Convolution as an Inception-like Unit

RepVGG. RepVGG: Making VGG-style ConvNets Great Again

vision_transformer. Jupyter Notebook

vit-pytorch. Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

Swin-Transformer. This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

SGNAS. [CVPR 2021] Searching by Generating: Flexible and Efficient One-Shot NAS with Architecture Generator

CTNAS. [CVPR 2021] Contrastive Neural Architecture Search with Neural Architecture Comparators

scutthesis. Latex/Lyx templates for the thesis specifications of South China University of Technology (SCUT,华南理工大学)

SCGN. Deep View Synthesis via Self-Consistent Generative Networks (TMM 2021)

DENet. This is the official repo for Dynamic Extension Nets for Few-shot Semantic Segmentation (ACM Multimedia 20).

aw_nas. aw_nas: A Modularized and Extensible NAS Framework

LCCGAN-v2. Pytorch implementation of LCCGAN++.

google-research. Google Research

DeepInversion. Official PyTorch implementation of Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion (CVPR 2020)

Awesome-Super-Resolution. Collect super-resolution related papers, data, repositories

CNAS. Breaking the Curse of Space Explosion: Towards Efficient NAS with Curriculum Search

once-for-all. [ICLR 2020] Once for All: Train One Network and Specialize it for Efficient Deployment

Efficient-AI-Backbones. Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.

DRN. Closed-loop Matters: Dual Regression Networks for Single Image Super-Resolution

mobilenetv3. mobilenetv3 with pytorch，provide pre-train model

HNAS-SR. HNAS: Hierarchical Neural Architecture Search for Single Image Super-Resolution

NATv2. Implementation for NATv2.

LCCGAN-v2. Code for “Improving Generative Adversarial Networks with Local Coordinate Coding”

personal_site. Source code for my OLD website (v1. Hugo Academic. v2 Hugo Apéro)

AGNet. The code of "Attention Guided Network for Retinal Image Segmentation" in MICCAI 2019

MWGAN. PyTorch implementation of "Multi-marginal Wasserstein GAN" (NeurIPS2019)

CAC. Python

NAT. Implementation for NAT.

multiwaybp. Implementations for Multi-way BP.

EDVR. Winning Solution in NTIRE19 Challenges on Video Restoration and Enhancement (CVPR19 Workshops) - Video Restoration with Enhanced Deformable Convolutional Networks. EDVR has been merged into BasicSR and this repo is a mirror of BasicSR.

pytorch. Tensors and Dynamic neural networks in Python with strong GPU acceleration

pytorch-a2c-ppo-acktr-gail. PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).

pygcn. Graph Convolutional Networks in PyTorch

models. Officially maintained, supported by PaddlePaddle, including CV, NLP, Speech, Rec, TS, big models and so on.

BasicSR. Open Source Image and Video Restoration Toolbox for Super-resolution, Denoise, Deblurring, etc. Currently, it includes EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, BasicVSR, SwinIR, ECBSR, etc. Also support StyleGAN2, DFDNet.

ESRGAN. ECCV18 Workshops - Enhanced SRGAN. Champion PIRM Challenge on Perceptual Super-Resolution. The training codes are in BasicSR.

Super-SloMo. PyTorch implementation of Super SloMo by Jiang et al.

DCP. Code for “Discrimination-aware-Channel-Pruning-for-Deep-Neural-Networks”

PocketFlow. An Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications.

darts. Differentiable architecture search for convolutional and recurrent networks

blocksparse. Efficient GPU kernels for block-sparse matrix multiplication and convolution

IGCV3. Code and Pretrained model for IGCV3

SparseConvNet. Submanifold sparse convolutional networks

LCCGAN. Code for “Adversarial Learning with Local Coordinate Coding”

AEGAN. Code for “Auto-Embedding Generative Adversarial Networks for High Resolution Image Synthesis”

DBPN-Pytorch. The project is an official implement of our CVPR2018 paper "Deep Back-Projection Networks for Super-Resolution" (Winner of NTIRE2018 and PIRM2018)

DRRN-pytorch. Pytorch implementation of Deep Recursive Residual Network for Super Resolution (DRRN), CVPR 2017

wae. Wasserstein Auto-Encoders

PyTorch-progressive_growing_of_gans. PyTorch implementation of Progressive Growing of GANs for Improved Quality, Stability, and Variation.

Detectron. FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

wgan-gp. A pytorch implementation of Paper "Improved Training of Wasserstein GANs"

progressive_growing_of_gans. Progressive Growing of GANs for Improved Quality, Stability, and Variation

HappyNet. Convolutional neural network that does real-time emotion recognition. HappyNet detects faces in video and images, classifies the emotion on each face, then replaces each face with the correct emoji for that emotion. Based on Caffe and the "Emotions in the Wild" network available on Caffe model zoo.

emotion-recognition-neural-networks. Emotion recognition using DNN with tensorflow

pytorch-CycleGAN-and-pix2pix. Image-to-Image Translation in PyTorch

wgan. Tensorflow Implementation of Wasserstein GAN (and Improved version in wgan_v2)

WGAN-tensorflow. a tensorflow implementation of WGAN

DCGAN-tensorflow. A tensorflow implementation of "Deep Convolutional Generative Adversarial Networks"

FastNeuralStyle. Fast Neural Style for Image Style Transform by Pytorch

the-incredible-pytorch. The Incredible PyTorch: a curated list of tutorials, papers, projects, communities and more relating to PyTorch.

subpixel. subpixel: A subpixel convnet for super resolution with Tensorflow

neural-enhance. Super Resolution for images using deep learning.

generative-models. Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.

pix2pix. Image-to-image translation with conditional adversarial nets

examples. A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

SRGAN. Torch implementation of SRGAN (Ledig et al., Photo -Realistic Single Image Super-Resolution Using a Generative Adversarial Network, 2016)

srez. Image super-resolution through deep learning

SelfExSR. Single Image Super-Resolution from Transformed Self-Exemplars (CVPR 2015)

Super-Resolution.Benckmark. Benchmark and resources for single super-resolution algorithms

torch-srgan. torch implementation of srgan

ademxapp. Code for https://arxiv.org/abs/1611.10080