Louis

cc-switch. A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io

Ref-L4. Evaluation code for Ref-L4, a new REC benchmark in the LMM era

refer. Referring Expression Datasets API

zsh. Shell

template-rust. Ultralytics Rust Package Template

inference. Rust inference package experiments

llm. Ultralytics LLM-related experiments

yoloe_data_engine. yoloe_data_engine

profile. Python

replicate. Deploy YOLO models to Replicate with ready-to-use Cog configurations and automated CI/CD. Includes optimized deployments for YOLO11, and reference implementations for custom model deployment.

mobileclip. Ultralytics implementation of the research paper, "MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training" CVPR 2024

autoimport. Effortless lazy Python imports

handbook. A guide to Ultralytics' mission, vision, values, and practices, providing key insights and resources for aligning with our goals.

notebooks. Ultralytics Notebooks 🚀

thop. Profile PyTorch models for FLOPs and parameters, helping to evaluate computational efficiency and memory usage.

source-trace. 🔍 Ultralytics Source Trace: A tool for detecting and analyzing code duplication across Git repositories.

CLIP. CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

yolo-flutter-app. Flutter plugin for Ultralytics YOLO

yolo-ios-app. Ultralytics YOLO iOS App source code for running YOLO in your own iOS apps 🌟

actions. Ultralytics GitHub Actions

template. Ultralytics Python Project Template

pre-commit. Ultralytics pre-commit hooks

hub-sdk. SDK for Ultralytics HUB

mkdocs. MkDocs plugin for Ultralytics Docs at https://docs.ultralytics.com

docs. Ultralytics Docs https://docs.ultralytics.com

ultralytics-ios-podspecs. Ultralytics iOS Pods

assets. Ultralytics assets

stars. Count GitHub Stars ⭐

hub. Ultralytics Platform tutorials and support

.github. Ultralytics GitHub default .github repository.

google-images-download. Google/Bing Images Web Downloader

flickr_scraper. Simple Flickr Image Scraper

JSON2YOLO. Convert COCO JSON to YOLO format

sandd. Python

iSky. Ultralytics iSky iOS app transforms your world into art with real-time style transfer.

ios_screenshots. Python

tinder. Official June 2018 Documentation for Tinder's API

yolov3. Ultralytics YOLOv3 in PyTorch > ONNX > CoreML > TFLite

xview-docker. xView 2018 Object Detection Challenge: Docker container submission code

mnist. MNIST Sandbox for testing neural network architectures.

xview-yolov3. xView 2018 Object Detection Challenge: YOLOv3 Training and Inference.

nudar. NeUtrino Detection and Ranging (NUDAR): earth modeling and neutrino detection simulation software

miniTimeCube. miniTimeCube (mTC) antineutrino detector simulation and analysis.

agm2015. AntiNeutrino Global Map (AGM) 2015 production code

ntc. Neutron TimeCube (NTC) neutron detector simulation and analysis

msvm. Minimum Separation Vector Mapping (MSVM)

functions-matlab. Common functions employed throughout various Ultralytics projects.

kinect. 3D Scene Reconstruction in MATLAB with the Microsoft Kinect depth sensor.

magellan. Earth observation software powered by Machine Learning (ML). Viewable in Google Maps and WebGL Earth.

petsys. LYSO-SiPM gamma scatter analysis from data collected by Ultralytics at PETSYS labs in Lisbon, Portugal, 2017.

wave. WAveform Vector Exploitation (WAVE): Machine Learning for particle physics detectors.

velocity. Structure From Motion (SFM) for vehicle speed

train_yoloe. a repo to record the yoloe training scripts

parpare_object365v1_withmask. Shell

flickr-dataset. Download flickr8k, flickr30k image caption datasets

rf-detr. RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning. [ICLR 2026]

AnomalyDINO. [WACV2025] AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2

interview-coder. An invisible desktop application to help you pass your technical interviews.

VRP-SAM. [CVPR 2024] Official implementation of "VRP-SAM: SAM with Visual Reference Prompt"

YOLO-World. [CVPR 2024] Real-Time Open-Vocabulary Object Detection

yoloe. YOLOE: Real-Time Seeing Anything [ICCV 2025]

VLM-R1. Solve Visual Understanding with Reinforced VLMs

ISAT_with_segment_anything. Labeling tool with SAM(segment anything model),supports SAM, SAM2, SAM3, sam-hq, MobileSAM EdgeSAM etc.交互式半自动图像标注工具

yolov12. [NeurIPS 2025] YOLOv12: Attention-Centric Real-Time Object Detectors

segment-anything-2-real-time. Run Segment Anything Model 2 on a live video stream

Hyper-YOLO. The source code of IEEE TPAMI 2025 "Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computation".

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.

Grounding-DINO-1.5-API. Grounding DINO 1.5: IDEA Research's Most Capable Open-World Object Detection Model Series

T-Rex. [ECCV2024] API code for T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy

DeepSeek-V3. Python

DINOv. [CVPR 2024] Official implementation of the paper "Visual In-context Learning"

DINO-X-API. DINO-X: The World's Top-Performing Vision Model for Open-World Object Detection and Understanding

FiLo. Official implementation of paper FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality Localization (ACM MM 2024).

EasyOCR. Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

MVTec-FS. The MVTec-FS dataset is a refined version of the MVTec AD dataset, designed for few-shot learning research.

jonbarron.github.io. HTML

academic-homepage. 🏡 GitHub Pages template for personal academic homepage

MVREC. Official source code for MVREC: A General Few-shot Defect Classification Model Using Multi-View Region-Context.(AAAI 2025)

LW-DETR. This repository is an official implementation of the paper "LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection".

Analytic-continual-learning. This repository will be posting analytic continual learning series, including Analytic Class-Incremental Learning (ACIL), Gaussian Kernel Embedded Analytic Learning (GKEAL), Dual-Stream Analytic Learning (DS-AL), etc.

Cool-GenAI-Fashion-Papers. [ACM TIST 2025] GenAI in Fashion: Overview, also includes 🔥latest papers, ⚙️metrics, 👀workshops, 🚀companies & products, ...)

LAMDA-PILOT. 🎉 PILOT: A Pre-trained Model-Based Continual Learning Toolbox

CALIP. [AAAI 2023] Zero-Shot Enhancement of CLIP with Parameter-free Attention

vowpal_wabbit. Vowpal Wabbit is a machine learning system which pushes the frontier of machine learning with techniques such as online, hashing, allreduce, reductions, learning2search, active, and interactive learning.

APE. [ICCV 2023] Code for "Not All Features Matter: Enhancing Few-shot CLIP with Adaptive Prior Refinement"

IndustrialTextileDataset. Introduction of new dataset for unsupervised fabric defect detection

IFDD. Few-shot Steel Surface Defect Detection

FSL_Cls_Screen. Python

CAML. Python

devit. CoRL 2024

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

awesome-few-shot-gnn. An index of algorithms for few-shot learning/meta-learning on graphs

Dino_V2. Dino V2 for Classification, PCA Visualization, Instance Retrival: https://arxiv.org/abs/2304.07193

WinClip. [CVPR 2023] Unofficial re-implementation of "WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation".

cpl. Code for Contrastive Preference Learning (CPL)

annotated_deep_learning_paper_implementations. 🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

open_spiel. OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.

rknn_model_zoo. C

Surface-Defect-Detection. 📈 目前最大的工业缺陷检测数据库及论文集 Constantly summarizing open source dataset and critical papers in the field of surface defect research which are of great importance.

ReContrast. [NeurIPS2023] Official Implementation of "ReContrast: Domain-Specific Anomaly Detection via Contrastive Reconstruction".

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

cvat. Computer Vision Annotation Tool (CVAT) is a leading platform for building high-quality visual datasets for vision AI. It offers open-source, cloud, and enterprise products, as well as labeling services, for image, video, and 3D annotation with AI-assisted labeling, quality assurance, team collaboration, analytics, and developer APIs.

FT-CLIP. CLIP Itself is a Strong Fine-tuner: Achieving 85.7% and 88.0% Top-1 Accuracy with ViT-B and ViT-L on ImageNet

flax. Flax is a neural network library for JAX that is designed for flexibility.

open_clip. An open source implementation of CLIP.

UNINEXT. [CVPR'23] Universal Instance Perception as Object Discovery and Retrieval

ZJU-Leaper-Dataset. This repository will provide codes of dataset API and some baseline experiments.

FastSAM. Fast Segment Anything

Segment-Everything-Everywhere-All-At-Once. [NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"

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

SimpleNet. Python

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

TensorRT-DETR. :zap::zap::zap:NVIDIA-阿里2021 TRT比赛 `二等奖` 代码提交 团队：美迪康 AI Lab :rocket::rocket::rocket:

RT-DETR. [CVPR 2024] Official RT-DETR (RTDETR paddle pytorch), Real-Time DEtection TRansformer, DETRs Beat YOLOs on Real-time Object Detection. 🔥 🔥 🔥

detr. End-to-End Object Detection with Transformers

openinterpreter. A lightweight coding agent for open models like Deepseek, Kimi, and Qwen

SAM-LST. Pytorch implementation of paper Ladder Fine-tuning approach for SAM integrating complementary network.

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

AnomalyGPT. [AAAI 2024 Oral] AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models

DeepSpeed. DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

awesome-industrial-anomaly-detection. Paper list and datasets for industrial image anomaly/defect detection (updating). 工业异常/瑕疵检测论文及数据集检索库(持续更新)。

Segment-Any-Anomaly. Official implementation of "Segment Any Anomaly without Training via Hybrid Prompt Regularization (SAA+)".

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.

TensorRT. NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

REB. REB：Reducing Biases in Representation for Industrial Anomaly Detection

ComAD. official code for paper entitled "Component-aware anomaly detection framework for adjustable and logical industrial visual inspection"

gpytorch. A highly efficient implementation of Gaussian Processes in PyTorch

cpl. Official Code of AAAI 2023 paper "Controlling Class Layout for Deep Ordinal Classification via Constrained Proxies Learning".

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

DRAEM. Python

flowgmm. Shell

frp. A fast reverse proxy to help you expose a local server behind a NAT or firewall to the internet.

CLIP. CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

infer. A new tensorrt integrate. Easy to integrate many tasks

ultralytics. Ultralytics YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking

SINBAD. A method for detecting anomalies consisting of unusual combinations of normal elements using set features

Fast-Poisson-Image-Editing. A fast poisson image editing implementation that can utilize multi-core CPU or GPU to handle a high-resolution image input.

cvpr-latex-template. Extended LaTeX template for CVPR/ICCV papers

ClusteringDirectionCentrality. A novel Clustering algorithm by measuring Direction Centrality (CDC) locally. It adopts a density-independent metric based on the distribution of K-nearest neighbors (KNNs) to distinguish between internal and boundary points. The boundary points generate enclosed cages to bind the connections of internal points.

hdbscan. A high performance implementation of HDBSCAN clustering.

pyod. A Python library for anomaly detection across tabular, time series, graph, text, image, and audio data. 60+ detectors, benchmark-backed ADEngine orchestration, and an agentic workflow for AI agents.

deepcluster. Deep Clustering for Unsupervised Learning of Visual Features

DeepClustering. Methods and Implements of Deep Clustering

gmm-torch. Gaussian mixture models in PyTorch.

dagmm. My attempt at reproducing the paper Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly Detection

perlin_noise. Smooth random noise generator

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

Memseg-Implementation. Unofficial individual re-implementation for "MemSeg: A semi-supervised method for image surface defect detection using differences and commonalities"

MemSeg. Unofficial re-implementation of MemSeg for Anomaly Detection

OpenOOD. Benchmarking Generalized Out-of-Distribution Detection

imgaug. Image augmentation for machine learning experiments.

swav. PyTorch implementation of SwAV https//arxiv.org/abs/2006.09882

FastFlow. Python

anomalib. An anomaly detection library comprising state-of-the-art algorithms and features such as experiment management, hyper-parameter optimization, and edge inference.

faiss. A library for efficient similarity search and clustering of dense vectors.

patchcore-inspection. Python

Deep-SVDD-PyTorch. A PyTorch implementation of the Deep SVDD anomaly detection method

Facial-Similarity-with-Siamese-Networks-in-Pytorch. Implementing Siamese networks with a contrastive loss for similarity learning

siamese-triplet. Siamese and triplet networks with online pair/triplet mining in PyTorch

SimCLR. PyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations

simclr. SimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learners

review_object_detection_metrics. Object Detection Metrics. 14 object detection metrics: mean Average Precision (mAP), Average Recall (AR), Spatio-Temporal Tube Average Precision (STT-AP). This project supports different bounding box formats as in COCO, PASCAL, Imagenet, etc.

Object-Detection-Metrics. Most popular metrics used to evaluate object detection algorithms.

SALOD. A benchmark for Salient Object Detection (SOD).

NotepadNext. A cross-platform, reimplementation of Notepad++

pytorch-center-loss. Pytorch implementation of Center Loss

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

pytorch-cutpaste. unoffical and work in progress PyTorch implementation of CutPaste

stb. stb single-file public domain libraries for C/C++

yt-dlp. A feature-rich command-line audio/video downloader

viewer. ML models and internal tensors 3D visualizer

awesome_lightweight_networks. The implementation of various lightweight networks by using PyTorch. such as：MobileNetV2，MobileNeXt，GhostNet，ParNet，MobileViT、AdderNet，ShuffleNetV1-V2，LCNet，ConvNeXt，etc. ⭐⭐⭐⭐⭐

pyTranscriber. pyTranscriber can be used to generate automatic transcription / automatic subtitles for audio/video files through a friendly graphical user interface.

vs2019_tensorRT_yolov5_dll_pro. C++

tensorRT_Pro. C++ library based on tensorrt integration

mmdetection. OpenMMLab Detection Toolbox and Benchmark

darknet. Convolutional Neural Networks

Tianchi_Fabric_defects_detection. 广东工业智造大赛--布匹瑕疵检测复赛代码

Tianchi-2019-Guangdong-Intelligent-identification-of-cloth-defects-rank5. 天池2019广东工业智造创新大赛 布匹疵点检测 天池水也太深了 季军解决方案

SingleClassRL. Code for weakly supervised segmentation of a single class

BaiduPCS. 百度网盘命令行工具。The terminal utility for Baidu Network Disk.

jupyterlab. JupyterLab computational environment.

ALAE. [CVPR2020] Adversarial Latent Autoencoders

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

OpencvDevelop. Qt+opencv制作的类似halcon的软件

res-unet_pytorch. 通过将残差网络作为编码器，改进UNet ( improving the unet by using the resnet as the encoder )

baseline_segment_Resunet_pytorch. a baseline for defect segmentation

pydensecrf. Python wrapper to Philipp Krähenbühl's dense (fully connected) CRFs with gaussian edge potentials.

Pytorch-UNet. PyTorch implementation of the U-Net for image semantic segmentation with high quality images

pytorch-fcn. PyTorch Implementation of Fully Convolutional Networks. (Training code to reproduce the original result is available.)

a_util_for_params. 自己写的一个工具类，方便管理和使用深度学习的各种超参数

Bilinear_ConvTranspose_pytorch. A implement of bilinear interpolation with ConvTranspose(用转置卷积实现双线性插值过程）

LCFCN. ECCV 2018 - Where are the Blobs: Counting by Localization with Point Supervision. This is a ServiceNow Research project that was started at Element AI.

MoNuSAC. This repository contains my implementations of the algorithms which MoNuSAC participants could use for data preparation to train their models at ISBI 2020.

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

Lip_Reading_Competition. 2019年“创青春.交子杯”新网银行高校金融科技挑战赛-AI算法赛道比赛_代码分享

temporal-shift-module. [ICCV 2019] TSM: Temporal Shift Module for Efficient Video Understanding

s3d.pytorch. Spatiotemporal-separable 3D convolution network.

DCNv2. Deformable Convolutional Networks v2 with Pytorch

surface-defect-detection. 缺陷检测文献记录