Starred repositories
70
results
for source starred repositories
written in Python
Clear filter
📚 Freely available programming books
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
OpenMMLab Detection Toolbox and Benchmark
deep learning for image processing including classification and object-detection etc.
Chat with your documents on your local device using GPT models. No data leaves your device and 100% private.
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
Image augmentation for machine learning experiments.
🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐
An open-source tool-augmented conversational language model from Fudan University
⛽️「算法通关手册」：从零开始的「算法与数据结构」学习教程，200 道「算法面试热门题目」，1000+ 道「LeetCode 题目解析」，持续更新中！
[ICLR 2026] RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning.
LightGlue: Local Feature Matching at Light Speed (ICCV 2023)
High-performance Inference and Deployment Toolkit for LLMs and VLMs based on PaddlePaddle
AdelaiDet is an open source toolbox for multiple instance-level detection and recognition tasks.
This repository includes the official project of TransUNet, presented in our paper: TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation.
pytorch tutorial for beginners
Unofficial PyTorch implementation of Masked Autoencoders Are Scalable Vision Learners
记录cv算法工程师的成长之路，分享计算机视觉和模型压缩部署技术栈笔记。https://harleyszhang.github.io/cv_note/
[CVPR 2025 Best Paper Nomination] FoundationStereo: Zero-Shot Stereo Matching
Scaled-YOLOv4: Scaling Cross Stage Partial Network
implementation of paper - You Only Learn One Representation: Unified Network for Multiple Tasks (https://arxiv.org/abs/2105.04206)
SOLO and SOLOv2 for instance segmentation, ECCV 2020 & NeurIPS 2020.
基于PaddleOCR重构，并且脱离PaddlePaddle深度学习训练框架的轻量级OCR，推理速度超快 —— A lightweight OCR system based on PaddleOCR, decoupled from the PaddlePaddle deep learning training framework, with ultra-fast inference speed.
网上搜集的自学python语言的资料集合,包括整套代码和讲义集合，这是至今为止所开放网上能够查找到的最新视频教程，网上找不到其他最新的python整套视频了,. 具体的无加密的mp4视频教程和讲义集合可以在更新的Readme文件中找到，下载直接打开就能播放，项目从零基础的Python教程到深度学习，总共30章节，其中包含Python基础中的飞机大战项目，WSGI项目，Flask新经资讯项目，…
Convert JSON annotations into YOLO format.
Code for our CVPR2021 paper coordinate attention