Knife丶

nano-vllm. Nano vLLM

deer-flow. An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

moyin-creator. AI 影视生产级工具 | 支持 Seedance 2.0 | 剧本到成片全流程批量化 | AI-powered film production tool with Seedance 2.0 support

lumenx. LumenX Studio，AI 短漫剧一站式生产平台。它能够将小说文本转化为动态视频，打通了从剧本分析、角色定制、分镜绘制到视频合成的完整创作链路。

ai-shotlive. AI 短剧，小说、剧本、分镜、提示词、关键帧、视频、AI剪辑的一站式服务。参考shuyu-labs/BigBanana-AI-Director、shamsharoon/CutOS、Will-Water/CineGen-AI以及HBAI-Ltd/Toonflow-app项目修改的。提供前后端分离和用户服务。

llm_wiki. LLM Wiki is a cross-platform desktop application that turns your documents into an organized, interlinked knowledge base — automatically. Instead of traditional RAG (retrieve-and-answer from scratch every time), the LLM incrementally builds and maintains a persistent wiki from your sources。

BigBanana-AI-Director. BigBanana AI Director是一个工业级一站式 AI 短剧，AI 漫剧,AI 导演平台，面向创作者，实现从灵感到成片的高效生产。 它摇弃了传统的“抽卡式”生成，采用 "Script-to-Asset-to-Keyframe" 的工业化工作流。实现 “一句话生成完整短剧，从剧本到成片全自动化”，同时精准控制角色一致性、场景连续性与镜头运动。

cs-notes. my cs notes

cursor-deepseek-v4-proxy. 解决 Cursor 使用 DeepSeek V4 模型时的 `reasoning_content must be passed back` 错误

skills. Skills for Real Engineers. Straight from my .agents directory.

vllm-plugin-FL. A vLLM plugin built on the FlagOS unified multi-chip backend.

clawbot. Clawdbot完整配置指南：从安装到Claude Code中转

fancyerii.github.io. HTML

pmpp. Complete solutions to the Programming Massively Parallel Processors Edition 4

Effective-Modern-Cpp. Sample code for the Effective Modern C++ book by Scott Meyers.

sol-tx-parser-capi. Python bindings for Solana Transaction Parser (tx-parser), enabling Python developers to easily parse and analyze Solana blockchain transactions.

soltxs. 📟 Solana transaction normalizer, parser, and resolver.

stealth.min.js. Automatically generate the newest stealth.min.js.

pjstealth. 浏览器特征抹除，及浏览器指纹随机化

Qbot. [🔥updating ...] AI 自动量化交易机器人(完全本地部署) AI-powered Quantitative Investment Research Platform. 📃 online docs: https://ufund-me.github.io/Qbot ✨ :news: qbot-mini: https://github.com/Charmve/iQuant

pointMLP-pytorch. [ICLR 2022 poster] Official PyTorch implementation of "Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework"

RSCNN_Pytorch1.0. Relation-Shape-CNN for Pytorch 1.0

PCT_Pytorch. Pytorch implementation of PCT: Point Cloud Transformer

SimpleView. Official Code for ICML 2021 paper "Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline"

CurveNet. [ICCV 2021] Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis

kapture. kapture is a file format as well as a set of tools for manipulating datasets, and in particular Visual Localization and Structure from Motion data.

python_cpp_example. An example of a hybrid python/C++ package with unit tests

FME. Fundamental matrix estimation using deep learning

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

Power-Iteration-SVD. Backpropagation-Friendly-Eigendecomposition

deepF_noCorrs. # Deep Fundamental Matrix Estimation without Correspondences

DeepE_noCor_Pytorch. Estimate the essential matrix from two input images following the paper Deep Fundamental Matrix Estimation without Correspondences

kornia. 🐍 Geometric Computer Vision Library for Spatial AI

Reinforced-Feature-Points. Reinforced Feature Points: Optimizing Feature Detection and Description for a High-Level Task

leetcode-master. 《代码随想录》LeetCode 刷题攻略：200道经典题目刷题顺序，共60w字的详细图解，视频难点剖析，50余张思维导图，支持C++，Java，Python，Go，JavaScript等多语言版本，从此算法学习不再迷茫！🔥🔥 来看看，你会发现相见恨晚！🚀

External-Attention-pytorch. 🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐

einops. Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)

LoFTR. Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021, T-PAMI 2022

d2-net. D2-Net: A Trainable CNN for Joint Description and Detection of Local Features

CVPR-2021-Papers.

SuperGluePretrainedNetwork. SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)

GDANet. Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloud. (AAAI2021)

SuperGlue_SuperPoint_MegaDepth. Python

AI-Job-Notes. AI算法岗求职攻略（涵盖准备攻略、刷题指南、内推和AI公司清单等资料）

Deep-Learning-Interview-Book. 深度学习面试宝典（含数学、机器学习、深度学习、计算机视觉、自然语言处理和SLAM等方向）

torch-vectorized. Fast analytical implementation of batch eigen-decomposition for 3x3 symmetric matrices with Pytorch. > 250x faster than regular Pytorch implementation of batch eigen-decomposition on GPU.

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

transformer-ut. Transformer & Universal transformer

awesome-point-cloud-analysis-2023. A list of papers and datasets about point cloud analysis (processing) since 2017. Update every day!

Geo-CNN-Pytorch-PYG. A Pytorch Implementation of “Modeling Local Geometric Structure of 3D Point Clouds using Geo-CNN”

nps. 一款轻量级、高性能、功能强大的内网穿透代理服务器。支持tcp、udp、socks5、http等几乎所有流量转发，可用来访问内网网站、本地支付接口调试、ssh访问、远程桌面，内网dns解析、内网socks5代理等等……，并带有功能强大的web管理端。a lightweight, high-performance, powerful intranet penetration proxy server, with a powerful web management terminal.

Disout. Code for AAAI 2020 paper, Beyond Dropout: Feature Map Distortion to Regularize Deep Neural Networks (Disout).

PointCNN.Pytorch. A PyTorch implemetation of PointCNN (CS294-131 Course Proj)

dgcnn. Python

Pointnet2_pytorch. PointNet and PointNet++ implemented by pytorch (no tf_opt)

SoTA-Point-Cloud. 🔥[IEEE TPAMI 2020] Deep Learning for 3D Point Clouds: A Survey

AI-Power. AI动力(AI Power) GPU云平台使用指南

Miao-A-SongHao-Linear-Algebra-Notes. 宋浩老师“惊叹号”系列《线性代数》网课笔记及时间点目录 Song hao "exclamation mark" series "linear algebra" course notes and time point directory

torch-points3d. Pytorch framework for doing deep learning on point clouds.

GS-Net. Geometry Sharing Network for 3D Point Cloud Classification and Segmentation

pytorch-rotationnet. Python

pointnet3. Pytorch implementation for pointnet1 + pointnet2(pointnet++).

pumpkin-book. 南瓜书：《机器学习》（西瓜书）公式详解

Relation-Shape-CNN. Relation-Shape Convolutional Neural Network for Point Cloud Analysis (CVPR 2019 Oral & Best paper finalist)

CVPR2019_PartNet. Code for PartNet: A Recursive Part Decomposition Network for Fine-grained and Hierarchical Shape Segmentation

Simplest-LeetCode-Cpp-Solutions. C++ 极简之路，用繁琐的语言做简单的事。Exploring the simplest and deepest way of Cpp.

awesome-graph-classification. A collection of important graph embedding, classification and representation learning papers with implementations.

websockets. Library for building WebSocket servers and clients in Python

apex. A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

pytorch_gpu_memory. pytorch gpu memory check

dgl. Python package built to ease deep learning on graph, on top of existing DL frameworks.

Pointnet_Pointnet2_pytorch. PointNet and PointNet++ implemented by pytorch (pure python) and on ModelNet, ShapeNet and S3DIS.

pytorch-lightning. Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

Pytorch-Perceptual-Losses-Style-Transfer-Attention-Capsule-Network. Pytorch - Perceptual Losses - Style Transfer - Attention Capsule Network

keops. KErnel OPerationS, on CPUs and GPUs, with autodiff and without memory overflows

semantic-segmentation-pytorch. Pytorch implementation for Semantic Segmentation/Scene Parsing on MIT ADE20K dataset

NetworkGraph. 基于D3.js的Neo4j网络图可视化(Visualization of Neo4j Network Graph Based on D3.js

Graph-Neural-Network-Review.

pytorch-handbook. pytorch handbook是一本开源的书籍，目标是帮助那些希望和使用PyTorch进行深度学习开发和研究的朋友快速入门，其中包含的Pytorch教程全部通过测试保证可以成功运行

3D-Machine-Learning. A resource repository for 3D machine learning

awesome-point-cloud-analysis. A list of papers and datasets about point cloud analysis (processing)

Clearest-LeetCode-Cpp-Solutions. Clearest LeetCode C++ Solutions. 本项目追求思路清晰，代码简洁。This project is intended to clarify the general problem solving ideas

AI-Paper-Drawer. 人工智能论文关键点集结。This project aims to collect key points of AI papers.

awesome-computer-vision. A curated list of awesome computer vision resources

All-Github-Emoji-Icons. A repo of every emoji icon as a separate file and commit.

pytorch_geometric. Graph Neural Network Library for PyTorch

Shortest-LeetCode-Python-Solutions. Leet Code 刷题笔记 - - 不求最快最省，但求最短最优雅，Shorter is better here.

leetcode. 👏🏻 leetcode solutions for Humans™

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

state-of-the-art-result-for-machine-learning-problems. This repository provides state of the art (SoTA) results for all machine learning problems. We do our best to keep this repository up to date. If you do find a problem's SoTA result is out of date or missing, please raise this as an issue or submit Google form (with this information: research paper name, dataset, metric, source code and year). We will fix it immediately.

README. README文件语法解读，即Github Flavored Markdown语法介绍

AdaBound. An optimizer that trains as fast as Adam and as good as SGD.

ImageAI. A python library built to empower developers to build applications and systems with self-contained Computer Vision capabilities

DPCNN-TextCNN-Pytorch-Inception. 本项目主要为针对DPCNN（Deep Pyramid Convolutional Neural Networks for Text Categorization ）文本分类（Text Classification）的论文复现以及基于知乎看山杯Inception的修改和复现，后者效果略优。

Kaggle-Quora-Insincere-Questions-Classification. 短文本分类，基于pytorch

PyTorchText. 1st Place Solution for Zhihu Machine Learning Challenge . Implementation of various text-classification models.(知乎看山杯第一名解决方案)

AdamBound-. Python

deep-text-classification-pytorch. Deep neural network text classification papers in PyTorch

TextClassificationImplement. ’达观杯‘文本智能处理挑战赛，文本分类任务的实现，包括一些传统的监督学习算法和深度学习算法，主要基于sklearn/xgb/lgb/pytorch包实现。

PyTorch-NLP. Basic Utilities for PyTorch Natural Language Processing (NLP)

transformers. 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

mixup-cifar10. mixup: Beyond Empirical Risk Minimization

2018-shenqi-image-classification. 2018 中国气象“神气”算法赛-第17名

ResidualAttentionNetwork-pytorch. a pytorch code about Residual Attention Network. This code is based on two projects from

pretrained-models.pytorch. Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.

YOLOv3_PyTorch. Full implementation of YOLOv3 in PyTorch