Use Claude Code, Codex, Pi, and OpenCode for free (1.3B+ free tokens) from your terminal, app, IDE, or phone like OpenClaw (voice supported)

利用 AI 大模型和自动化工作流，根据主题或关键词一键生成高清短视频。Generate HD short videos from a topic or keyword with an automated AI workflow.

所有小初高、大学PDF教材。

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

Tailor是一款视频智能裁剪、视频生成和视频优化的视频剪辑工具。目前的目标是通过人工智能技术减少视频剪辑的繁琐操作，让普通人也能简单实现专业剪辑人的水准！长远目标是让视频剪辑实现真正的AIGC！

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

巴菲特 价值投资

RK3588 模型转换脚本——后处理修改

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

Object detection on multiple datasets with an automatically learned unified label space.

目标检测+目标跟踪+单目测距+姿态识别+车道线识别+车牌识别+A star算法+车辆跟踪与测距等视觉项目

[CVPR 2021] Self-supervised depth estimation from short sequences

light-weight 98 points face landmark超轻98点人脸关键点检测模型

nniefacelib是一个在海思35xx系列芯片上运行的人脸算法库

MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO、GRPO。

The BlazeFace face detector model implemented in PyTorch

An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.

基于Yolov5车牌检测,更快更准.

mediapipe-hand，mediapipe-body，mediapipe-face, mediapipe-embedding, mediapipe-classifier and so on.MNN inference

alibaba MNN, mobilenet classifier, centerface detecter, ultraface detecter, pfld landmarker and zqlandmarker, mobilefacenet

A curated list of resources dedicated to table recognition

Table Transformer (TATR) is a deep learning model for extracting tables from unstructured documents (PDFs and images). This is also the official repository for the PubTables-1M dataset and GriTS ev…

A collection of original, innovative ideas and algorithms towards Advanced Literate Machinery. This project is maintained by the OCR Team in the Language Technology Lab, Tongyi Lab, Alibaba Group.

PyTorch implementation of YOLOv5, YOLOv6, YOLOv7, YOLOv8, Sort, StrongSort, OcSort, ByteTrack, Norfair

Ready-to-use realtime multi-object tracker that works for any object category. YOLOv5 + SORT implementation.

A c++ implementation of yolov5 and deepsort

The deployment of deep learning model inference on the C++platform includes some common CV and NLP tasks.

针对pytorch模型的自动化模型结构分析和修改工具集，包含自动分析模型结构的模型压缩算法库

YOLO ModelCompression MultidatasetTraining