Hzzone

hello-agents. 📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程

drawio-mcp. JavaScript

RecommenderSystem.

Flash-RL. Implementation for FP8/INT8 Rollout for RL training without performence drop.

Recommender_System. 推荐系统入门指南，全面介绍了工业级推荐系统的理论知识（王树森推荐系统公开课-基于小红书的场景讲解工业界真实的推荐系统），如何基于TensorFlow2训练模型，如何实现高性能、高并发、高可用的Golang推理微服务。Comprehensively introduced the theory of industrial recommender system, how to trainning models based on TensorFlow2, how to implement the high-performance、high-concurrency and high-available inference services base on Golang.

nano-vllm. Nano vLLM

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。

M2F2_Det. 🔥Deepfake + LLM (CVPR25 Oral)

promptimizer. Prompt optimization scratch

go-cursor-help. 解决Cursor在免费订阅期间出现以下提示的问题: Your request has been blocked as our system has detected suspicious activity / You've reached your trial request limit. / Too many free trial accounts used on this machine.

YoLLaVA. 🌋👵🏻 Yo'LLaVA: Your Personalized Language and Vision Assistant (NeurIPS 2024)

RAP-MLLM. [CVPR 2025] RAP: Retrieval-Augmented Personalization

PetFace. [ECCV 2024 Oral] PetFace: A Large-Scale Dataset and Benchmark for Animal Identification https://arxiv.org/abs/2407.13555

Tamm_Code. [CVPR 2024] TAMM: TriAdapter Multi-Modal Learning for 3D Shape Understanding

Dense-Face. Face Generation Work (Preprint)

leetcode-notes. 🐳 LeetCode 算法笔记：面试、刷题、学算法。在线阅读地址：https://datawhalechina.github.io/leetcode-notes/

flow_matching. A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.

mar. PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838

flux. Official inference repo for FLUX.1 models

Scrapegraph-ai. Python scraper based on AI

HiFi_IFDL. 🔥Hierarchical Fine-Grained Image Forgery Detection and Localization (CVPR23 + IJCV24)

youtube-search-python. 🔎 Search for YouTube videos, channels & playlists. Get 🎞 video & 📑 playlist info using link. Get search suggestions. WITHOUT YouTube Data API v3.

youtube-dl. Command-line program to download videos from YouTube.com and other video sites

ByteTrack. [ECCV 2022] ByteTrack: Multi-Object Tracking by Associating Every Detection Box

ImageReward. [NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation

bypy. Python client for Baidu Yun (Personal Cloud Storage) 百度云/百度网盘Python客户端

alist. 🗂️A file list/WebDAV program that supports multiple storages, powered by Gin and Solidjs. / 一个支持多存储的文件列表/WebDAV程序，使用 Gin 和 Solidjs。

MiVOLO. MiVOLO age & gender transformer neural network

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

peewee. a small, expressive orm -- supports postgresql, mysql, sqlite, now with asyncio

lmdeploy. LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

ollama. Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

img2dataset. Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

gpt_academic. 为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, moss等。

dinov2. PyTorch code and models for the DINOv2 self-supervised learning method.

ViT-Adapter. [ICLR 2023 Spotlight] Vision Transformer Adapter for Dense Predictions

opensphere. A hyperspherical face recognition library based on PyTorch

MIGC. [CVPR 2024 Highlight] MIGC and [TPAMI 2024] MIGC++ (Official Implementation)

one-api. LLM API 管理 & 分发系统，支持 OpenAI、Azure、Anthropic Claude、Google Gemini、DeepSeek、字节豆包、ChatGLM、文心一言、讯飞星火、通义千问、360 智脑、腾讯混元等主流模型，统一 API 适配，可用于 key 管理与二次分发。单可执行文件，提供 Docker 镜像，一键部署，开箱即用。LLM API management & key redistribution system, unifying multiple providers under a single API. Single binary, Docker-ready, with an English UI.

GLIGEN. Open-Set Grounded Text-to-Image Generation

langchain. The agent engineering platform.

T2I-CompBench. [Neurips 2023 & TPAMI] T2I-CompBench (++) for Compositional Text-to-image Generation Evaluation

llama. Inference code for Llama models

Awesome-Multimodal-Large-Language-Models. :sparkles::sparkles:Latest Advances on Multimodal Large Language Models

everyone-can-use-english. 人人都能用英语

WeChatExtension-ForMac. A plugin for Mac WeChat

NextChat. ✨ Light and Fast AI Assistant. Support: Web | iOS | MacOS | Android | Linux | Windows

PseCo. (CVPR 2024) Point, Segment and Count: A Generalized Framework for Object Counting

Joint-Learning-for-Alzheimer-disease. [MedIA 2024] This is a code implemention of the joint learning framework proposed in the manuscipt "Joint learning framework of cross-modal synthesis and diagnosis for Alzheimer's disease by mining underlying shared modality information".

Grounded-Segment-Anything. Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

ExplainableVQA. [ACMMM Oral, 2023] "Towards Explainable In-the-wild Video Quality Assessment: A Database and a Language-Prompted Approach"

DOVER. [ICCV 2023, Official Code] for paper "Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives". Official Weights and Demos provided.

FAST-VQA-and-FasterVQA. [ECCV2022, TPAMI2023] FAST-VQA, and its extended version FasterVQA.

Q-Bench. ①[ICLR2024 Spotlight] (GPT-4V/Gemini-Pro/Qwen-VL-Plus+16 OS MLLMs) A benchmark for multi-modality LLMs (MLLMs) on low-level vision and visual quality assessment.

Detic. Code release for "Detecting Twenty-thousand Classes using Image-level Supervision".

SDFlow. Jupyter Notebook

CHSNet. Source code for ICASSP'23 paper: Cross-head Supervision for Crowd Counting with Noisy Annotations

OnPro. Online Prototype Learning for Online Continual Learning (ICCV 2023)

AdaTrans. Adaptive Nonlinear Latent Transformation for Conditional Face Editing (ICCV 2023)

segment_anything_streamlit_webui. This is a streamlit web interface for the Segment Anything.

labelme. Image annotation with Python. Supports polygon, rectangle, circle, line, point, and AI-assisted annotation.

copy-paste-aug. Copy-paste augmentation for segmentation and detection tasks

chatgpt-review-rebuttal-extension. ChatGPT - Review & Rebuttal: A browser extension for generating reviews and rebuttals, powered by ChatGPT. 利用 ChatGPT 生成审稿意见和回复的浏览器插件

detr. End-to-End Object Detection with Transformers

ghost. A new one shot face swap approach for image and video domains

CenterNet. Object detection, 3D detection, and pose estimation using center point detection:

pytorch-ddpm. Unofficial PyTorch implementation of Denoising Diffusion Probabilistic Models

TCL. Twin Contrastive Learning with Noisy Labels (CVPR 2023)

bob-plugin-openai-translator. 基于 LLM 的文本翻译、文本润色、语法纠错 Bob 插件，让我们一起迎接不需要巴别塔的新时代！Licensed under CC BY-NC-SA 4.0

SAN. Python

nextai-translator. 基于 ChatGPT API 的划词翻译浏览器插件和跨平台桌面端应用 - Browser extension and cross-platform desktop application for translation based on ChatGPT API.

PlayCover. Community fork of PlayCover

nonlinear-image-editing. Jupyter Notebook

torchdiffeq. Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.

normalizing-flows-pytorch. PyTorch implementations of normalizing flow and its variants.

torch_clustering. A pure PyTorch implementation of kmeans and GMM with distributed clustering.

ProPos. Self-Supervised Learning for Deep Clustering (TPAMI 2022)

wandb. The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.

SummaryOfLoanSuspension. 全国各省市停贷通知汇总

ccf-deadlines. ⏰ Agenticly track worldwide conference deadlines (Website, Python Cli, Wechat Applet)

glance. 🔎 All-in-one Quick Look plugin

ssl_bad_gan. Good Semi-Supervised Learning That Requires a Bad GAN

stylegan2-ada-pytorch. StyleGAN2-ADA - Official PyTorch implementation

mixup-cifar10. mixup: Beyond Empirical Risk Minimization

mae-scalable-vision-learners. A TensorFlow 2.x implementation of Masked Autoencoders Are Scalable Vision Learners

python-varname. Dark magics about variable names in python

DREAM. This is the official code repository for the paper "Deep Rank-Consistent Pyramid Model for Better Crowd Counting".

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

cleanlab. Cleanlab's open-source library is the standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.

jupyterlab-vim. Vim notebook cell bindings for JupyterLab

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

dino. PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

deepface. A Lightweight Face Recognition and Facial Attribute Analysis (Age, Gender, Emotion and Race) Library for Python

oni2. Native, lightweight modal code editor

mmselfsup. OpenMMLab Self-Supervised Learning Toolbox and Benchmark

stylegan2-pytorch. Implementation of Analyzing and Improving the Image Quality of StyleGAN (StyleGAN 2) in PyTorch

BYOL-PyTorch. PyTorch implementation of "Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning" with DDP and Apex AMP

stylegan3. Official PyTorch implementation of StyleGAN3

anonymous_github. Anonymous Github is a proxy server to support anonymous browsing of Github repositories for open-science code and data.

Long-Tailed-Recognition.pytorch. [NeurIPS 2020] This project provides a strong single-stage baseline for Long-Tailed Classification, Detection, and Instance Segmentation (LVIS). It is also a PyTorch implementation of the NeurIPS 2020 paper 'Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect'.

DU-GAN. DU-GAN: Generative Adversarial Networks with Dual-Domain U-Net Based Discriminators for Low-Dose CT Denoising

fvcore. Collection of common code that's shared among different research projects in FAIR computer vision team.

projector-docker. Run JetBrains IDEs remotely with Docker

make-sense. Free to use online tool for labelling photos. https://makesense.ai

spherical_kde. Kernel density estimation on a sphere

IB-INN. Code for the paper "Training Normalizing Flows with the Information Bottleneck for Competitive Generative Classification" (2020)

glow. Implementation of Glow in PyTorch

AgeFlow. AgeFlow: Conditional Age Progression and Regression with Normalizing Flows (IJCAI 2021)

awesome-normalizing-flows. Awesome resources on normalizing flows.

spherecluster. Clustering routines for the unit sphere

power_spherical. Pytorch implementation of the Power Spherical distribution

MTLFace. When Age-Invariant Face Recognition Meets Face Age Synthesis: A Multi-Task Learning Framework (CVPR 2021 oral & TPAMI 2022)

mean-teacher. A state-of-the-art semi-supervised method for image recognition

SAGAN. Sharpness-aware Low Dose CT Denoising Using Conditional Generative Adversarial Network

PyTorch-StudioGAN. StudioGAN is a Pytorch library providing implementations of representative Generative Adversarial Networks (GANs) for conditional/unconditional image generation.

everybody_dance_now_pytorch. A PyTorch Implementation of "Everybody Dance Now" from Berkeley AI lab.

DFDNet. Blind Face Restoration via Deep Multi-scale Component Dictionaries (ECCV 2020)

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.

playwright-python. Python version of the Playwright testing and automation library.

EDAR. PyTorch implementation of Deep Convolution Networks based on EDSR for Compression(Jpeg) Artifacts Reduction

glow. Code for reproducing results in "Glow: Generative Flow with Invertible 1x1 Convolutions"

celebA-HQ-dataset-download. Get started with CelebA-HQ dataset in under 5 mins !

macfuse. macFUSE umbrella repository

glow-pytorch. PyTorch implementation of Glow

pix2pix-flow. Image-to-image translation with flow-based generative model

unetgan. Official Implementation of the paper "A U-Net Based Discriminator for Generative Adversarial Networks" (CVPR 2020)

Offline-Reinforcement-Learning. Collecting Offline/Batch Reinforcement Learning Paper

stylegan2-pytorch. Simplest working implementation of Stylegan2, state of the art generative adversarial network, in Pytorch. Enabling everyone to experience disentanglement

GON. Gradient Origin Networks - a new type of generative model that is able to quickly learn a latent representation without an encoder

drawio-desktop. Official electron build of draw.io

kornia. 🐍 Geometric Computer Vision Library for Spatial AI

CurricularFace. CurricularFace(CVPR2020)

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

EverybodyDanceNow. Motion Retargeting Video Subjects

qlib. Qlib is an AI-oriented Quant investment platform that aims to use AI tech to empower Quant Research, from exploring ideas to implementing productions. Qlib supports diverse ML modeling paradigms, including supervised learning, market dynamics modeling, and RL, and is now equipped with https://github.com/microsoft/RD-Agent to automate R&D process.

dissect. Code for the Proceedings of the National Academy of Sciences 2020 article, "Understanding the Role of Individual Units in a Deep Neural Network"

github-readme-stats. :zap: Dynamically generated stats for your github readmes

mimicry. [CVPR 2020 Workshop] A PyTorch GAN library that reproduces research results for popular GANs.

CIDA. [ICML 2020] Continuously Indexed Domain Adaptation

InfoDrop. Code for our paper "Informative Dropout for Robust Representation Learning: A Shape-bias Perspective" (ICML 2020)

open-styleganv2-pytorch. Open source + Free for Commercial Use implementation of StyleGANv2 in pytorch

RealnessGAN. Code for ICLR2020 paper 'Real or Not Real, that is the Question'

minGPT. A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

cavaface. face recognition training project(pytorch)

zotero. Zotero is a free, easy-to-use tool to help you collect, organize, annotate, cite, and share your research sources.

attention-module. Official PyTorch code for "BAM: Bottleneck Attention Module (BMVC2018)" and "CBAM: Convolutional Block Attention Module (ECCV2018)"

awesome-domain-adaptation. A collection of AWESOME things about domain adaptation

pytorch-memonger. Sublinear memory optimization for deep learning. https://arxiv.org/abs/1604.06174

imagededup. 😎 Finding duplicate images made easy!

google-images-download. Python Script to download hundreds of images from 'Google Images'. It is a ready-to-run code!

CosFace_pytorch. Pytorch implementation of CosFace

scripts. Shadowsocks/SS一键脚本、ShadowsocksR/SSR一键脚本、V2Ray一键脚本、trojan一键脚本、VPS教程

amazon-a2i-sample-task-uis. Over 60 example task UIs for Amazon Augmented AI (A2I)

insightface. State-of-the-art 2D and 3D Face Analysis Project

MaoZeDongAnthology. 毛泽东选集

SCUT-FBP5500-Database-Release. A diverse benchmark database for multi-paradigm facial beauty prediction

LaTeXTableEditor. readme

DG-Net. :couple: Joint Discriminative and Generative Learning for Person Re-identification. CVPR'19 (Oral) :couple:

skipnet. Code for SkipNet: Learning Dynamic Routing in Convolutional Networks (ECCV 2018)

pytorch-ssim. pytorch structural similarity (SSIM) loss

big-discriminator-batch-spoofing-gan. BMSG-GAN with more features

dynamic_net. Official pyTorch implementation of "Dynamic-Net: Tuning the Objective Without Re-training for Synthesis Tasks" experiments

SSR-Net. [IJCAI18] SSR-Net: A Compact Soft Stagewise Regression Network for Age Estimation

TaskRouting. (ICCV 2019 Oral) Many Task Learning With Task Routing http://openaccess.thecvf.com/content_ICCV_2019/html/Strezoski_Many_Task_Learning_With_Task_Routing_ICCV_2019_paper.html

deep-image-prior. Image restoration with neural networks but without learning.

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

bottom-up-features. Bottom-up features extractor implemented in PyTorch.

LipGAN. This repository contains the codes for LipGAN. LipGAN was published as a part of the paper titled "Towards Automatic Face-to-Face Translation".

Speech-Emotion-Analyzer. The neural network model is capable of detecting five different male/female emotions from audio speeches. (Deep Learning, NLP, Python)

sigsep-mus-db. Python parser and tools for MUSDB18 Music Separation Dataset

mml-book.github.io. Companion webpage to the book "Mathematics For Machine Learning"

ganhacks. starter from "How to Train a GAN?" at NIPS2016

fearless. A dashboard scaffolding based on Vue.js 3.x & TypeScript created by Vite.

lets-plot. Multiplatform plotting library based on the Grammar of Graphics

artipub. Article publishing platform that automatically distributes your articles to various media channels

reconstructing_faces_from_voices. [NeurIPS 2019] Face Reconstruction from Voice using Generative Adversarial Networks

labelImgPlus. :metal: LabelImgPlus is a graphical image annotation tool which supports CLS,DET and SEG

pytorch-generative-model-collections. Collection of generative models in Pytorch version.

inception-score-pytorch. Inception Score for GANs in Pytorch

pytorch-spectral-normalization-gan. Paper by Miyato et al. https://openreview.net/forum?id=B1QRgziT-

tf.gans-comparison. Implementations of (theoretical) generative adversarial networks and comparison without cherry-picking

talks. Jupyter Notebook

ClassyVision. An end-to-end PyTorch framework for image and video classification

SinGAN. Official pytorch implementation of the paper: "SinGAN: Learning a Generative Model from a Single Natural Image"

evil-huawei. Evil Huawei - 华为作过的恶

DALI. A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.

PyTorch-GAN. PyTorch implementations of Generative Adversarial Networks.

awesome-semantic-segmentation-pytorch. Semantic Segmentation on PyTorch (include FCN, PSPNet, Deeplabv3, Deeplabv3+, DANet, DenseASPP, BiSeNet, EncNet, DUNet, ICNet, ENet, OCNet, CCNet, PSANet, CGNet, ESPNet, LEDNet, DFANet)

pytorch-gradual-warmup-lr. Gradually-Warmup Learning Rate Scheduler for PyTorch

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

pytorch-OpCounter. Count the MACs / FLOPs of your PyTorch model.

rufus. The Reliable USB Formatting Utility

MAP-NN. Source code of MAP-NN paper

PRML. PRML algorithms implemented in Python

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

python-facepp. Library for communicating with a Face++ facial recognition service

IPCGANs-Pytorch. An implementation of《Face Aging with Identity-Preserved Conditional Generative Adversarial Networks》

Dive-into-DL-PyTorch. 本项目将《动手学深度学习》(Dive into Deep Learning)原书中的MXNet实现改为PyTorch实现。

LearingFaceAgeProgression. Learning Face Age Progression: A Pyramid Architecture of GANs, CVPR 2018

pytorch-DEX. Pytorch implementation of DEX: Deep EXpectation of apparent age from a single image