Peng Sun

self-llm. 《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程

ACoT-VLA. [CVPR 2026] Official implementation of "ACoT-VLA: Action Chain-of-Thought for Vision-Language-Action Models"

SparseDrive. SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representation

Build-A-Large-Language-Model-CN. 《Build a Large Language Model (From Scratch)》是一本深入探讨大语言模型原理与实现的电子书，适合希望深入了解 GPT 等大模型架构、训练过程及应用开发的学习者。为了让更多中文读者能够接触到这本极具价值的教材，我决定将其翻译成中文，并通过 GitHub 进行开源共享。

LLMs-from-scratch. Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

awesome-LLM-resources. 🧑‍🚀 全世界最好的LLM资料总结（多模态生成、Agent、辅助编程、AI审稿、数据处理、模型训练、模型推理、o1 模型、MCP、小语言模型、视觉语言模型） | Summary of the world's best LLM resources.

openclaw. Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

awesome-openclaw-skills. The awesome collection of OpenClaw skills. 5,400+ skills filtered and categorized from the official OpenClaw Skills Registry.🦞

clawhub. Skill + Plugin Registry for OpenClaw

claw-code. An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

le-wm. Official code base for LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

py-futu-api. 富途 OpenAPI Python SDK

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

abu. 阿布量化交易系统(股票，期权，期货，比特币，机器学习) 基于python的开源量化交易，量化投资架构

vnpy. 基于Python的开源量化交易平台开发框架

VADv2. End-to-End Vectorized Autonomous Driving via Probabilistic Planning

DiffusionDrive. [CVPR 2025 Highlight] Truncated Diffusion Model for Real-Time End-to-End Autonomous Driving

VLA-OS. Official Code For VLA-OS.

MapTR. [ICLR'23 Spotlight & ECCV'24 & IJCV'24] MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction

Sparse4D. Jupyter Notebook

ai-hedge-fund. An AI Hedge Fund Team

DriveLM. [ECCV 2024 Oral] DriveLM: Driving with Graph Visual Question Answering

End-to-end-Autonomous-Driving. [IEEE T-PAMI 2024] All you need for End-to-end Autonomous Driving

VAD. [ICCV 2023 & ICLR 2026] VAD: Vectorized Scene Representation for Efficient Autonomous Driving

Awesome-Chinese-LLM. 整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

yolov10. YOLOv10: Real-Time End-to-End Object Detection [NeurIPS 2024]

Depth-Anything. [CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation

UniAD. [CVPR 2023 Best Paper Award] Planning-oriented Autonomous Driving

bevfusion. [ICRA'23] BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation

Deformable-DETR. Deformable DETR: Deformable Transformers for End-to-End Object Detection.

MetaGPT. 🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

SparkDesk-Java. 讯飞星火大模型Java SDK 易开发，更灵活. Xun fei SparkDesk Java SDK. SparkDesk. xfyun SDK. xinghuo.星火.

dify. Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.

mamba-minimal. Simple, minimal implementation of the Mamba SSM in one file of PyTorch.

huggingface_hub. The official CLI and Python client for the Hugging Face Hub.

PaddleSpeech. Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.

espnet. End-to-End Speech Processing Toolkit

TTS. 🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

Chinese-FastSpeech2. 基于标贝数据继续训练，同时对原本的FastSpeech2模型做了改进，引入了韵律表征以及韵律预测模块，使中文发音更生动且富有节奏

FastSpeech2. An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"

youtube-shorts-generator. YouTube Shorts videos generator using ChatGPT, Bing, GTTS, OpenAI's Whisper, MoviePy and Python

gTTS. Python library and CLI tool to interface with Google Translate's text-to-speech API

whisperX. WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

pyttsx3. Offline Text To Speech synthesis for python

Speech-and-Text. Speech to text (PocketSphinx, Iflytex API, Baidu API) and text to speech (pyttsx3) | 语音转文字（PocketSphinx、百度 API、科大讯飞 API）和文字转语音（pyttsx3）

stt. Voice Recognition to Text Tool / 一个离线运行的本地音视频转字幕工具，输出json、srt字幕、纯文字格式

AutoGPT. AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

grok-1. Grok open release

uni-app. A cross-platform framework using Vue.js

DeepSeek-Coder. DeepSeek Coder: Let the Code Write Itself

fastapi. FastAPI framework, high performance, easy to learn, fast to code, ready for production

Llama-Chinese. Llama中文社区，实时汇总最新Llama学习资料，构建最好的中文Llama大模型开源生态，完全开源可商用

ItChat-UOS. 复活Itchat,你只需要 pip install itchat-uos

CowAgent. Open-source super AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-model, multi-channel. Lightweight, extensible, one-line install. (formerly chatgpt-on-wechat)

wechat-miniapp-radar. 小程序雷达：AI 驱动的小程序技术选型、趋势追踪和迁移诊断工具

wechat-need-web. 让微信网页版可用 / Allow the use of WeChat via webpage access

ItChat. A complete and graceful API for Wechat. 微信个人号接口、微信机器人及命令行微信，三十行即可自定义个人号机器人。

WeixinBot. 网页版微信API，包含终端版微信及微信机器人

WeChatRobot. 微信HOOK、微信机器人 wxhook，数据库解密 微信公众号采集 微信公众号爬虫，企业微信HOOK

CVPR2023-3D-Occupancy-Prediction. CVPR2023-Occupancy-Prediction-Challenge

VoxFormer. Official PyTorch implementation of VoxFormer [CVPR 2023 Highlight]

MOSS. An open-source tool-augmented conversational language model from Fudan University

Fast-BEV. Fast-BEV: A Fast and Strong Bird’s-Eye View Perception Baseline

WoodScape. The repository containing tools and information about the WoodScape dataset.

BagofTricks-LT. A scientific and useful toolbox, which contains practical and effective long-tail related tricks with extensive experimental results

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

ModelSoups. ModelSoups for Tensorflow2 and Torch

RegNet. Implementation of RegNet (Tensorflow)

VectorMapNet_code. This is the official code base of VectorMapNet (ICML 2023)

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.

PolarMask. Code for 'PolarMask: Single Shot Instance Segmentation with Polar Representation'

yolov7. Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

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

OpenLane. [ECCV 2022 Oral] OpenLane: Large-scale Realistic 3D Lane Dataset

TimeSformer. The official pytorch implementation of our paper "Is Space-Time Attention All You Need for Video Understanding?"

scenic. Scenic: A Jax Library for Computer Vision Research and Beyond

python-2.5-annotated. python-2.5-annotated

detr-tensorflow. Tensorflow implementation of DETR : Object Detection with Transformers

BEVFormer. [ECCV 2022] This is the official implementation of BEVFormer, a camera-only framework for autonomous driving perception, e.g., 3D object detection and semantic map segmentation.

hyperopt. Distributed Asynchronous Hyperparameter Optimization in Python

pytorch-auto-drive. PytorchAutoDrive: Segmentation models (ERFNet, ENet, DeepLab, FCN...) and Lane detection models (SCNN, RESA, LSTR, LaneATT, BézierLaneNet...) based on PyTorch with fast training, visualization, benchmarking & deployment help

YOLOX. YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

PRML. PRML algorithms implemented in Python

CenterTrack. Simultaneous object detection and tracking using center points.

AttentionConvLSTM. "Attention in Convolutional LSTM for Gesture Recognition" in NIPS 2018

Gestureness. Learning Spatiotemporal Features using 3DCNN and Convolutional LSTM

Conv3D_CLSTM. Multimodal Gesture Recognition Using 3D Convolution and Convolutional LSTM

ContinuousGR. Continuous Gesture Segmentation and Recognition using 3DCNN and Convolutional LSTM

Conv3D_BICLSTM. Learning Spatiotemporal Features using 3DCNN and Convolutional LSTM for Gesture Recognition

ConvLSTMForGR. Redundancy and Attention in Convolutional LSTM for Gesture Recognition

yolov5-face. YOLO5Face: Why Reinventing a Face Detector (https://arxiv.org/abs/2105.12931) ECCV Workshops 2022)

mmaction. An open-source toolbox for action understanding based on PyTorch

LateTemporalModeling3DCNN. Python

yolov5. Ultralytics YOLOv5 in PyTorch for object detection, instance segmentation, classification, training, and export.

tfyolo. tfyolo: Efficient Implementation of Yolov5 in TensorFlow

YOLOv5-tf. YOLOv5 implementation using TensorFlow 2

Yolov5_Tensorflow. Yolov5 tensorflow实现

resa. Implementation of our paper 'RESA: Recurrent Feature-Shift Aggregator for Lane Detection' in AAAI2021.

LSTR. This is an official repository of End-to-end Lane Shape Prediction with Transformers.

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

LaneAF. Python

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

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）

multi_threading. :construction:《C++并发编程实战》的读书笔记，供以后工作中查阅。

TensorFlow2.0_ResNet. A ResNet(ResNet18, ResNet34, ResNet50, ResNet101, ResNet152) implementation using TensorFlow-2.0.

tensorflow2.0-examples. Jupyter notebooks to help you started with tensorflow 2.0

TensorFlow2.0-Examples. 🙄 Difficult algorithm, Simple code.

keras-YOLOv3-model-set. end-to-end YOLOv4/v3/v2 object detection pipeline, implemented on tf.keras with different technologies

PolyLaneNet. Code for the paper entitled "PolyLaneNet: Lane Estimation via Deep Polynomial Regression" (ICPR 2020)

hawp. Holistically-Attracted Wireframe Parsing [TPAMI'23] & [CVPR' 20]

Unified-Line-Segment-Detection. Unified Line Segment Detection

Pytorch_Generalized_3D_Lane_Detection. [ECCV 2020] Official PyTorch implementation of "Gen-LaneNet: a generalized and scalable approach for 3D lane detection"

Ultra-Fast-Lane-Detection. Ultra Fast Structure-aware Deep Lane Detection (ECCV 2020)

SCNN. Spatial CNN for traffic lane detection (AAAI2018)

LaneATT. Code for the paper entitled "Keep your Eyes on the Lane: Real-time Attention-guided Lane Detection" (CVPR 2021)

PINet_new. Python

darknet. YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet )

ScaledYOLOv4. Scaled-YOLOv4: Scaling Cross Stage Partial Network

pytorch-YOLOv4. PyTorch ,ONNX and TensorRT implementation of YOLOv4

TensorFlow-2.x-Tutorials. TensorFlow 2.x version's Tutorials and Examples, including CNN, RNN, GAN, Auto-Encoders, FasterRCNN, GPT, BERT examples, etc. TF 2.0版入门实例代码，实战教程。

Yolov5_tf. Yolov5/Yolov4/ Yolov3/ Yolo_tiny in tensorflow

tensorflow-yolov4-tflite. YOLOv4, YOLOv4-tiny, YOLOv3, YOLOv3-tiny Implemented in Tensorflow 2.0, Android. Convert YOLO v4 .weights tensorflow, tensorrt and tflite

PyTorchTricks. Some tricks of pytorch... :star:

mmdetection-to-tensorrt. convert mmdetection model to tensorrt, support fp16, int8, batch input, dynamic shape etc.

OpenPCDet. OpenPCDet Toolbox for LiDAR-based 3D Object Detection.

PointRCNN. PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud, CVPR 2019.

second.pytorch. PointPillars for KITTI object detection

mmskeleton. A OpenMMLAB toolbox for human pose estimation, skeleton-based action recognition, and action synthesis.

mmpretrain. OpenMMLab Pre-training Toolbox and Benchmark

mmsegmentation. OpenMMLab Semantic Segmentation Toolbox and Benchmark.

mmdetection3d. OpenMMLab's next-generation platform for general 3D object detection.

pointnet2. PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space

pointnet. PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

PAA. A PyTorch implementation of the paper `Probabilistic Anchor Assignment with IoU Prediction for Object Detection` ECCV 2020 (https://arxiv.org/abs/2007.08103)

RepPointsV2. Python

CVPR2026-Papers-with-Code. CVPR 2026 论文和开源项目合集

DetectoRS. DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution

FixRes. This repository reproduces the results of the paper: "Fixing the train-test resolution discrepancy" https://arxiv.org/abs/1906.06423

Yet-Another-EfficientDet-Pytorch. The pytorch re-implement of the official efficientdet with SOTA performance in real time and pretrained weights.

SegmenTron. Support PointRend, Fast_SCNN, HRNet, Deeplabv3_plus(xception, resnet, mobilenet), ContextNet, FPENet, DABNet, EdaNet, ENet, Espnetv2, RefineNet, UNet, DANet, HRNet, DFANet, HardNet, LedNet, OCNet, EncNet, DuNet, CGNet, CCNet, BiSeNet, PSPNet, ICNet, FCN, deeplab)

design-patterns-py. 《大话设计模式》Python实现

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

Pytorch_Retinaface. Retinaface get 80.99% in widerface hard val using mobilenet0.25.

CVPR2024-Paper-Code-Interpretation. cvpr2024/cvpr2023/cvpr2022/cvpr2021/cvpr2020/cvpr2019/cvpr2018/cvpr2017 论文/代码/解读/直播合集，极市团队整理

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

GCNv2_SLAM. Real-time SLAM system with deep features

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

SuperPoint_SLAM. SuperPoint + ORB_SLAM2

HRNet-Semantic-Segmentation. The OCR approach is rephrased as Segmentation Transformer: https://arxiv.org/abs/1909.11065. This is an official implementation of semantic segmentation for HRNet. https://arxiv.org/abs/1908.07919

Semantic-Segmentation-Suite. Semantic Segmentation Suite in TensorFlow. Implement, train, and test new Semantic Segmentation models easily!

segmentation_models. Segmentation models with pretrained backbones. Keras and TensorFlow Keras.

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)

segmentation_models.pytorch. Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

awesome-semantic-segmentation. :metal: awesome-semantic-segmentation

detectron2. Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

CS-Book. 计算机类常用电子书整理，并且附带下载链接，包括Java，Python，Linux，Go，C，C++，数据结构与算法，人工智能，计算机基础，面试，设计模式，数据库，前端等书籍

colmap. COLMAP - Structure-from-Motion and Multi-View Stereo

intelligent_scissors_5421spring2018. Python

polyrnn-pp. Inference Code for Polygon-RNN++ (CVPR 2018)

polyrnn-pp-pytorch. PyTorch training/tool code for Polygon-RNN++ (CVPR 2018)

Interactive_Segmentation_Models. Literature Review for Interactive annotation/segmentation

Intseg. Interactive Image Segmentation with Latent Diversity

BRS-Interactive_segmentation. Won-Dong Jang and Chang-Su Kim, "Interactive Image Segmentation via Backpropagating Refinement Scheme," CVPR 2019

bdd_segmentation. BDD data Drivable Area Segmentation;ai challenger

BDCN. The code for the CVPR2019 paper Bi-Directional Cascade Network for Perceptual Edge Detection

DexiNed. DexiNed: Dense EXtreme Inception Network for Edge Detection

awesome-object-detection. Awesome Object Detection based on handong1587 github: https://handong1587.github.io/deep_learning/2015/10/09/object-detection.html

EfficientNet-PyTorch. A PyTorch implementation of EfficientNet

kaolin. A PyTorch Library for Accelerating 3D Deep Learning Research

Res2Net-PretrainedModels. (ImageNet pretrained models) The official pytorch implemention of the TPAMI paper "Res2Net: A New Multi-scale Backbone Architecture"

albumentations_gui. GUI for albumentations library

albumentations. Fast and flexible image augmentation library. Paper about the library: https://www.mdpi.com/2078-2489/11/2/125

CenterNet. Codes for our paper "CenterNet: Keypoint Triplets for Object Detection" .

PreciseRoIPooling. Precise RoI Pooling with coordinate gradient support, proposed in the paper "Acquisition of Localization Confidence for Accurate Object Detection" (https://arxiv.org/abs/1807.11590).

fastai. The fastai deep learning library

gluon-cv. Gluon CV Toolkit

Counting-with-Focus-for-Free. Code for Counting with Focus for Free, ICCV, 2019

SNIPER. SNIPER / AutoFocus is an efficient multi-scale object detection training / inference algorithm

awesome-lane-detection. A paper list of lane detection.

Codes-for-Lane-Detection. Learning Lightweight Lane Detection CNNs by Self Attention Distillation (ICCV 2019)

siammask_e. This is the add-on package for the pysot project. SiamMask_E is an updated version of SiamMask with ellipse fitting and bounding box scale refinement.

3d-vehicle-tracking. Official implementation of Joint Monocular 3D Vehicle Detection and Tracking (ICCV 2019)

SST. Single Shot Tracker

wireframe. Python

afm_cvpr2019. Official implementation of paper "Learning Attraction Field Map for Robust Line Segment Detection" (CVPR 2019)

PPGNet. Source code for our CVPR 2019 paper - PPGNet: Learning Point-Pair Graph for Line Segment Detection

lcnn. LCNN: End-to-End Wireframe Parsing

DataLoaders_DALI. PyTorch DataLoaders implemented with DALI for accelerating image preprocessing

learned-correspondence-release. Code release for "learning to find good correspondences" CVPR 2018

cnn_lstm_ctc_ocr_for_ICPR. Forked from weinman/cnn_lstm_ctc_ocr for the ICPR MTWI 2018 challenge 1

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

libpku. 贵校课程资料民间整理

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

SJTU-Courses. 上海交通大学课程资料分享

USTC-Course. :heart:中国科学技术大学课程资源

kalman_filter_multi_object_tracking. Multiple object tracking using Kalman Filter and Hungarian Algorithm - OpenCV

mcf-tracker. A simple multi-object tracker based on the mcf library

multi-object-tracking. yolov3, deep_sort and optical flow

arxiv.py. Python wrapper for the arXiv API

ALiPy. ALiPy: Active Learning in Python is an active learning python toolbox, which allows users to conveniently evaluate, compare and analyze the performance of active learning methods.