E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance Segmentation

《李宏毅深度学习教程》（李宏毅老师推荐👍，苹果书🍎），PDF下载地址：https://github.com/datawhalechina/leedl-tutorial/releases

Soybean seed localization and counting based on dot annotated infield images

免费开源A股量化数据库； 专注A股，专注量化，向阳而生； 开放、纯净、持续、为Ai(爱)发电。为个人量化交易而生，保卫3000(2500)点，珍惜底部机会......【股票数据，股票行情数据，股票量化数据，股票交易数据，k线行情数据，股票概念数据，股票数据接口，行情数据接口】【多数据源融合，动态设置代理，保障数据高可用性】

Ultralytics YOLO11 🚀

Hash3D: Training-free Acceleration for 3D Generation

JNeRF is a NeRF benchmark based on Jittor. JNeRF re-implemented instant-ngp and achieved same performance with original paper.

Instant neural graphics primitives: lightning fast NeRF and more

Phenotyping all the aspects of soybean (Outdoor, Indoor, Detection, Segmentation, Seed testing, Node num, etc.)

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

A LITE BERT FOR SELF-SUPERVISED LEARNING OF LANGUAGE REPRESENTATIONS, 海量中文预训练ALBERT模型

公用的bing/chatgpt接入点

A deep learning-based tool to identify splice variants

Create more effcient super-resolution model for plant images!

Inference code for Llama models

🚀 一键部署！真正的 AI 聊天机器人！支持ChatGPT、文心一言、讯飞星火、Bing、Bard、ChatGLM、POE，多账号，人设调教，虚拟女仆、图片渲染、语音发送 | 支持 QQ、Telegram、Discord、微信 等平台

Reverse engineered API of Microsoft Copilot AI

MCP-Reborn is an MCP (Mod Coder Pack) for Minecraft for making modded clients and researching its code. (1.13-1.20.1)

Counting wheat heads using a simulation model

Awesome List of Attention Modules and Plug&Play Modules in Computer Vision

PointCloud analysis focus on solving 3D plant phenotypes

Modular and ready to deploy code to detect and track videos using YOLO-v7 and DeepSORT

End2End Multi-View Feature Matching with Differentiable Pose Optimization

Unofficial implementation of ZipNeRF

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

vits2 backbone with multilingual-bert

OpenFace – a state-of-the art tool intended for facial landmark detection, head pose estimation, facial action unit recognition, and eye-gaze estimation.