2D Optical flow using NVIDIA CUDA

CUDA implementation of the paper "Fast Edge-Preserving PatchMatch for Large Displacement Optical Flow" in CVPR 2014.

本项目基于matlab的dftregistration函数。主要用于解决由于外部因素导致的图像错位，帮助其进行矫正。提供CUDA版本和C++版本

A C CUDA implementation of the Lucas Kanade Optical Flow Algorithm

用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.

https://www.kaggle.com/competitions/image-matching-challenge-2022

Methods for alignment of global image statistics aimed at unsupervised Domain Adaptation and Data Augmentation

Superpoint and Superglue training and testing code, also some traditional method (SIFT and ORB)

数字摄影测量影像相关系数匹配和最小二乘匹配

This is a toolbox repository to help evaluate various methods that perform image matching from a pair of images.

C++ implementation of a ScienceDirect paper "An accelerating cpu-based correlation-based image alignment for real-time automatic optical inspection"

Feature Detection and Description with SIFT, SURF, KAZE, BRIEF, ORB, BRISK, AKAZE and FREAK using Python and OpenCV

MobileSAM already integrated into Personalize Segment Anything Model (SAM) with 1 shot in 10 seconds

This is a collection of our NAS and Vision Transformer work.

This is the official code for MobileSAM project that makes SAM lightweight for mobile applications and beyond!

Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)

中文聊天小模型，用t5 base在大量数据上有监督。

基于ChatGLM-6B的中文问诊模型

LLM inference in C/C++

Instruct-tune LLaMA on consumer hardware

The simplest way to run LLaMA on your local machine

A collection of resources and papers on Diffusion Models

The simplest, fastest repository for training/finetuning medium-sized GPTs.

The official implementation of "Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes"

🐰 Python lib for remo - the app for annotations and images management in Computer Vision

根据Pytorch官方教程实现 Mask-RCNN，其 backbone为ResNet50+FPN。现在完成了对于示例数据集的训练，后续会继续修改，实现其他的功能。

git-repo is a command-line tool for centralized workflow, can work with Gerrit, AGit-Flow compatible servers. It is written in Golang, and it can be installed easily without further dependency. It …

End-to-End Object Detection with Transformers

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.

A PyTorch implementation of the architecture of Mask RCNN