CHAN.K

AI-Scientist-v2. The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search

ai-guide. 程序员鱼皮的 AI 资源大全 + Vibe Coding 零基础教程，分享 OpenClaw 保姆级教程、大模型玩法（DeepSeek / GPT / Gemini / Claude / GLM）、最新 AI 资讯、Prompt 提示词大全、AI 知识百科（Agent Skills / RAG / MCP / A2A）、AI 编程教程（Harness Engineering）、AI 工具用法（Cursor / Claude Code / TRAE / Codex / Copilot）、AI 开发框架教程（Spring AI / LangChain）、AI 产品变现指南，帮你快速掌握 AI 技术，走在时代前沿。本项目为开源文档 aiguide，已升级为鱼皮 AI 导航网站

scientific-agent-skills. Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 160,000+ scientists worldwide. 140 ready-to-use skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.

skills. Give your agents the power of the Hugging Face ecosystem

ai-agents-for-beginners. 12 Lessons to Get Started Building AI Agents

annas-to-notebooklm. Python

HY-WorldPlay. HY-World 1.5: A Systematic Framework for Interactive World Modeling with Real-Time Latency and Geometric Consistency

ICLR2025-Papers-with-Code. 历年ICLR论文和开源项目合集，包含ICLR2021、ICLR2022、ICLR2023、ICLR2024、ICLR2025.

Loop. Window management made elegant.

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

pytorch-image-models. The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

SegWithDistMap. How Distance Transform Maps Boost Segmentation CNNs: An Empirical Study

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

torchvista. Interactive Pytorch forward pass visualization in notebooks

vision_transformer. Jupyter Notebook

Reinforcement-Learning. 大三下强化学习作业集合

TextDiff. 【MICCAI 2024, Early Accept】Enhancing Label-efficient Medical Image Segmentation with Text-guided Diffusion Models

PDF-Extract-Kit. A Comprehensive Toolkit for High-Quality PDF Content Extraction

NJUAI-Notes. 我在南京大学人工智能专业学习时所做的笔记 :-)

LIC_TCM. Python

paper-reading-note. 和李沐一起读论文

Semantic-SAM. [ECCV 2024] Official implementation of the paper "Semantic-SAM: Segment and Recognize Anything at Any Granularity"

U-KAN. [AAAI' 25] U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation

SSR-V2ray-Trojan. 2026机场推荐与机场评测

medico-sam. Segment Anything for Medical Imaging

USTC-Course. :heart:中国科学技术大学课程资源

transferlearning. Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials.-迁移学习

SAM2Point. The Most Faithful Implementation of Segment Anything (SAM) in 3D

STAR. [ICCV 2025] STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolution

segmentation_metrics. A package to compute medical segmentation metrics.

Awesome-AIGC. AIGC资料汇总学习，持续更新......

segment-anything. The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

genesis-world. Simulation platform for general-purpose robotics & embodied AI learning.

llm-cookbook. 面向开发者的 LLM 入门教程，吴恩达大模型系列课程中文版

Cutie. [CVPR 2024 Highlight] Putting the Object Back Into Video Object Segmentation

EfficientSAM. EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything

MedSAM. Segment Anything in Medical Images

SAM4MIS. Segment Anything Model for Medical Image Segmentation: Open-Source Project Summary

KiU-Net-pytorch. Official Pytorch Code of KiU-Net for Image/3D Segmentation - MICCAI 2020 (Oral), IEEE TMI

CausalLLMs-ReadingGroup. repository for Causal&NLP reading group

PyMIC. Python

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.

instanseg. Python

SOTA-MedSeg. SOTA medical image segmentation methods based on various challenges

MedSAM-U. Python

leedl-tutorial. 《李宏毅深度学习教程》（李宏毅老师推荐👍，苹果书🍎），PDF下载地址：https://github.com/datawhalechina/leedl-tutorial/releases

LURE. [ICLR 2024] Analyzing and Mitigating Object Hallucination in Large Vision-Language Models

PSDDSAM.

Multimodal-Affective-Computing-Survey.

PUNETR. Python

megvii-tsinghua-dl-course. Slides with modifications for a course at Tsinghua University.

3DSAM-adapter. Holistic Adaptation of SAM from 2D to 3D for Promptable Medical Image Segmentation

deep-learning-for-image-processing. deep learning for image processing including classification and object-detection etc.

SAMed. The implementation of the technical report: "Customized Segment Anything Model for Medical Image Segmentation"

samm. A 3D Slicer integration to Meta's SAM.

wesam. [CVPR 2024] Code for "Improving the Generalization of Segmentation Foundation Model under Distribution Shift via Weakly Supervised Adaptation"

TinySAM. [AAAI 2025] Official PyTorch implementation of "TinySAM: Pushing the Envelope for Efficient Segment Anything Model"

CE-Net. 【TMI】This repo is for CENet, which is accepted in TMI.

lora. Using Low-rank adaptation to quickly fine-tune diffusion models.

UNet3plus_pth. UNet3+/ UNet++/UNet, used in Deep Automatic Portrait Matting in Pytorth

MoneyPrinterTurbo. 利用AI大模型，一键生成高清短视频 Generate short videos with one click using AI LLM.

grok-1. Grok open release

SimpleCVPaperReading. :smile:博客论文列表：分系列整理

LoRA. Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

Medical-SAM-Adapter. A lightweight adapter bridges SAM with medical imaging [MedIA]

HAT. CVPR2023 - Activating More Pixels in Image Super-Resolution Transformer TPAMI - HAT: Hybrid Attention Transformer for Image Restoration

lungmask. Automated lung segmentation in CT

VM-UNet. (ACM TOMM) This is the official code repository for "VM-UNet: Vision Mamba UNet for Medical Image Segmentation".

UNet-Version. Python

ParC-Net. [ECCV 2022] Source code of "EdgeFormer: Improving Light-weight ConvNets by Learning from Vision Transformers"

Plug-and-Play. 深度学习中各种即插即用小模块

Plug-and-Play. 深度学习中各种即插即用小模块

dl-template. deep learning template code

clipseg. This repository contains the code of the CVPR 2022 paper "Image Segmentation Using Text and Image Prompts".

segmentation_in_style. https://arxiv.org/abs/2107.12518

ZegCLIP. Official implement of CVPR2023 ZegCLIP: Towards Adapting CLIP for Zero-shot Semantic Segmentation

SA-UNet-PyTorch. SA-UNet Impleneted By PyTorch

Swin-Unet. [ECCVW 2022] The codes for the work "Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation"

Medical-Transformer. Official Pytorch Code for "Medical Transformer: Gated Axial-Attention for Medical Image Segmentation" - MICCAI 2021

PhotoMaker. PhotoMaker [CVPR 2024]

-python. 超级玛丽

DARC. Decentralized Autonomous Regulated Company (DARC), a company virtual machine that runs on any EVM-compatible blockchain, with on-chain law system, multi-level tokens and dividends mechanism.

gpt-2. Code for the paper "Language Models are Unsupervised Multitask Learners"

ChatGPT. 🔮 ChatGPT Desktop Application (Mac, Windows and Linux)

center_line_extract. Binarize the vector road surface data raster, extract the road skeleton line with the help of the skimage library, and finally vectorize the road centerline raster data and retain the spatial information

How-to-run. 立党零基础转码笔记

raft-thesis-zh_cn. Raft 博士论文的中文翻译

MiBio-OCR-dataset. Python

civil-service-exam. 考试攻略 | 公务员 | 事业单位

SMSBomber. 一个短信轰炸机程序，不得利用本程序做违法的事, 使用本程序所产生的任何后果本人都不承担任何责任

HEU_KMS_Activator.

deep-transfer-learning. A collection of implementations of deep domain adaptation algorithms

SMSBoom. SMSBoom - Deprecate: Due to judicial reasons, the repository has been suspended!

civil-service-exam. 公务员考试知识思维导图，我们岸上见！

backend-interview. 后端面试题汇总（Python、Redis、MySQL、PostgreSQL、Kafka、数据结构、算法、编程、网络）

dev-sidecar. 开发者边车，github打不开，github加速，git clone加速，git release下载加速，stackoverflow加速

pytorch-pyramid-pooling. This Module implements Spatial Pyramid Pooling (SPP) and Temporal Pyramid Pooling (TPP) as described in different papers.

WZU-machine-learning-course. 温州大学《机器学习》课程资料（代码、课件等）

wenku_spider. 免券下载百度文库，支持doc,txt,ppt,pdf

WiFiBroot. A Wireless (WPA/WPA2) Pentest/Cracking tool. Captures & Crack 4-way handshake and PMKID key. Also, supports a deauthentication/jammer mode for stress testing

iptv. Collection of publicly available IPTV channels from all over the world

nlp_paper_study. 该仓库主要记录 NLP 算法工程师相关的顶会论文研读笔记

YYeTsBot. 🎬 人人影视 机器人和网站，包含人人影视全部资源以及众多网友的网盘分享

coder2gwy. 互联网首份程序员考公指南，由3位已经进入体制内的前大厂程序员联合献上。

v2simple. A simple implementation of V2Ray.

PyTorch_Tutorial. 《Pytorch模型训练实用教程》中配套代码

ShelfNet. implementation for paper "ShelfNet for fast semantic segmentation"

stock. 30天掌握量化交易 (持续更新)

PyTorch-Image-Classification. 基于PyTorch框架实现的图像分类网络

segmentation-learning-experiment. 基于Pytorch框架的语义分割学习，FCN，UNet，DeepLab 基于VOC数据集。

pyda-2e-zh. :book: [译] 利用 Python 进行数据分析 · 第 2 版

UNET-ZOO. including unet,unet++,attention-unet,r2unet,cenet,segnet ,fcn.

hyperspec-fcn. Using FCN and an Attention layer to recognize Hyperdimensional images

notebook. Jupyter Interactive Notebook

AlgoNotes. 【浅梦学习笔记】文章汇总:包含 排序&CXR预估，召回匹配，用户画像&特征工程，推荐搜索综合 计算广告，大数据，图算法，NLP&CV，求职面试 等内容

MegEngine. MegEngine 是一个快速、可拓展、易于使用且支持自动求导的深度学习框架

PKUAutoSubmit. PKU一键出入校备案小工具

Data-Structres. 浙江大学《数据结构》上课笔记 + 数据结构实现 + 课后题题解

Chinese_emotion_predict. Predict Chinese sentence's emotion. 中文情绪识别

MRI-U-net. 基于U-net和MRI图像的膀胱壁边缘以及膀胱肿瘤检测

Yolo-Fastest. :zap: Based on yolo's ultra-lightweight universal target detection algorithm, the calculation amount is only 250mflops, the ncnn model size is only 666kb, the Raspberry Pi 3b can run up to 15fps+, and the mobile terminal can run up to 178fps+

yolov5. Ultralytics YOLOv5 in PyTorch > ONNX > CoreML > TFLite

YOLO-v5. :art: Pytorch YOLO v5 训练自己的数据集超详细教程！！！ :art: (提供PDF训练教程下载）

DeepLearning. Python for《Deep Learning》，该书为《深度学习》(花书) 数学推导、原理剖析与源码级别代码实现

n3net. Neural Nearest Neighbors Networks (NIPS*2018)

pytorch-book. PyTorch tutorials and fun projects including neural talk, neural style, poem writing, anime generation (《深度学习框架PyTorch：入门与实战》)

notes-python. 中文 Python 笔记

covid19_critically_ill. Trained model and inference code for early triage of critically-ill COVID-19 patients.

Machine-Learning-Algorithm. 机器学习（统计方法+深度学习）理论方法+技术实战、数据集资源、学习方法和技术客栈

tensorRT. TensorRT-7 Network Lib 包括常用目标检测、关键点检测、人脸检测、OCR等 可训练自己数据

SMS_Bomber. 短信轰炸机，可以给定多个手机号，疯狂发送验证码。This is a short message bomber.

COVID-Net. COVID-Net Open Source Initiative

ttfnet. Python

ocr-rcnn-v2. Elevator Button Recognition, Tensorflow1.12 on TX2, OCR RCNN

VDB-EDT. An efficient and robust framework for occupancy grid mapping and Euclidean distance transform

CT-image-segmentation-and-lymphatic-metastasis-in-rectal-cancer. Jupyter Notebook

Efficient-Segmentation-Networks. Lightweight models for real-time semantic segmentationon PyTorch (include SQNet, LinkNet, SegNet, UNet, ENet, ERFNet, EDANet, ESPNet, ESPNetv2, LEDNet, ESNet, FSSNet, CGNet, DABNet, Fast-SCNN, ContextNet, FPENet, etc.)

Tmall_SSM. 模仿天猫项目SSM版（前端+后台）

zhihu-huawei251. 自动发布知乎试图打压的内容

SparseCNN. Implementation of Sparse CNN

machine-learning-yearning-cn. Machine Learning Yearning 中文版 - 《机器学习训练秘籍》 - Andrew Ng 著

torchcv. TorchCV: A PyTorch-Based Framework for Deep Learning in Computer Vision

Data-Science-Notes. 数据科学的笔记以及资料搜集

yolov3-mobilenet-v1. Python

python-filter. Python

imgaug. Image augmentation for machine learning experiments.

region_growing_dcm. Python UI library for 3D-DCM-based region growing

ImageCaptioning.pytorch. I decide to sync up this repo and self-critical.pytorch. (The old master is in old master branch for archive)

ChineseNLP. Datasets, SOTA results of every fields of Chinese NLP

stat212b. Topics Course on Deep Learning UC Berkeley

Predict_Coronary_Heart_Disease. Capstone Project for the Flatiron School Data Science Bootcamp Immersive Program

HarmonyOS. A curated list of awesome things related to HarmonyOS. 华为鸿蒙操作系统。

MedicalNet. Many studies have shown that the performance on deep learning is significantly affected by volume of training data. The MedicalNet project provides a series of 3D-ResNet pre-trained models and relative code.

FCN-pytorch. 🚘 Easiest Fully Convolutional Networks

Apollo-11. Original Apollo 11 Guidance Computer (AGC) source code for the command and lunar modules.

lihang_book_algorithm. 致力于将李航博士《统计学习方法》一书中所有算法实现一遍

CoronaryArteryCenterline. Coronary artery centerline extraction from CT image (.mha format) 从心脏CT图像提取冠状动脉中心线

pulmonary-nodules-segmentation. Tianchi medical AI competition [Season 1]: Lung nodules image segmentation of U-Net. U-Net训练基于卷积神经网络的肺结节分割器

CT_Semantic_Segmentation. Contains codes for algorithms used to delineate organs from CT images for thoracic patients in radiation treatment planning

CT_Semantic_Segmentation. Contains codes for algorithms used to delineate organs from CT images for thoracic patients in radiation treatment planning

Awesome-PyTorch-Chinese. 【干货】史上最全的PyTorch学习资源汇总

AG-CNN. The model of "Attention Based Glaucoma Detection: A Large-scale Database with a CNN Model" (CVPR2019)

terminal. The new Windows Terminal and the original Windows console host, all in the same place!

programming-note. Programming-Note-Gitbook

crnn.pytorch. Convolutional recurrent network in pytorch

v2ray-core. A platform for building proxies to bypass network restrictions.

flutter-netease-music. flutter music player application. (仿网易云音乐)

Mask_RCNN. Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

pytorch-semantic-segmentation. PyTorch for Semantic Segmentation

simple-orm. Mini ORM

REKCARC-TSC-UHT. 清华大学计算机系课程攻略 Guidance for courses in Department of Computer Science and Technology, Tsinghua University

pix2pixHD. Synthesizing and manipulating 2048x1024 images with conditional GANs

3D_GAN_Lung_Nodules. GAN code for generating lung nodule ct scans

Retina-VesselNet. A Simple U-net model for Retinal Blood Vessel Segmentation based on tensorflow2

retina-unet. Retina blood vessel segmentation with a convolutional neural network

ImageProcessingProjects. Image processing using python and opencv

efanna_graph. an Extremely Fast Approximate Nearest Neighbor graph construction Algorithm framework

FaceBagNet. FaceBagNet - Patch-based Methods for Multi-modal Face Anti-spoofing (FAS)

zju-icicles. 浙江大学课程攻略共享计划

955.WLB. 955 不加班的公司名单 - 工作 955，work–life balance (工作与生活的平衡)

LeetCodeAnimation. Demonstrate all the questions on LeetCode in the form of animation.（用动画的形式呈现解LeetCode题目的思路,完整单步/回看/变速/语音讲解在 algomooc.com）

nndl. 邱锡鹏《神经网络与深度学习》（蒲公英书）理论书 v2 与通识版

DeepLearning-500-questions. 深度学习500问，以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述，以帮助自己及有需要的读者。 全书分为18个章节，50余万字。由于水平有限，书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作，联系scutjy2015@163.com 版权所有，违权必究 Tan 2018.06

pumpkin-book. 南瓜书：《机器学习》（西瓜书）公式详解

996.ICU. Repo for counting stars and contributing. Press F to pay respect to glorious developers.

Real-Time-Emotion-Detection-for-Classroom-Crowd-Analysis. Python

seat-detection-and-scene-perception. 实现教室内座位的自动识别和标注，基于openCV和python 3.5

face_reg. 毕设练习-人脸识别检测

pytorch-semantic-segmentation. segmentation repo using pytorch

pytorch-semseg. Semantic Segmentation Architectures Implemented in PyTorch

libpku. 贵校课程资料民间整理

opencv. Open Source Computer Vision Library

lingvo. Lingvo

pytorch-tutorial. PyTorch Tutorial for Deep Learning Researchers

Paddle. PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）

image-classification-CIFAR10-tf. Simple Image Classification Models for the CIFAR-10 dataset using TensorFlow

GPF. GPF（Graph Processing Flow）：利用图神经网络处理问题的一般化流程

ReadingNotes. 小萌的读书笔记

Skill-Tree. 🐼 准备秋招，欢迎来树上取果实

deeplearningAI. The DeepLearning AI Courses of Andrew Ng