Popular GitHub Repositories for Samd21

PJON (Padded Jittering Operative Network) is an experimental, arduino-compatible, multi-master, multi-media network protocol.

Official code of "HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation", CVPR 2021

[CVPR 2021] Multi-Stage Progressive Image Restoration. SOTA results for Image deblurring, deraining, and denoising.

Jenetics - Genetic Algorithm, Genetic Programming, Grammatical Evolution, Evolutionary Algorithm, and Multi-objective Optimization

Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection, CVPR2021

TOOD: Task-aligned One-stage Object Detection, ICCV2021 Oral

Autocomplete your obsidian notes with AI, including ChatGPT, through a copilot-like interface.

CoMoGAN: continuous model-guided image-to-image translation. CVPR 2021 oral.

利用MoneyPrinterTurbo自动生成动态视频（非PPT念稿式），并整合万兴AI的文本转视频和图片转视频功能作为素材，从而丰富素材库，灵活控制视频生成过程。

? Building Go applications with LLMs through composability

(Experimental, a lot of bugs) Automatic fingering generator for piano scores, determining optimal fingering using Model-Based Reinforcement Learning, written in the Julia language.

A simple NPM interface for seamlessly interacting with 36 Large Language Model (LLM) providers, including OpenAI, Anthropic, Google Gemini, Cohere, Hugging Face Inference, NVIDIA AI, Mistral AI, AI21 Studio, LLaMA.CPP, and Ollama, and hundreds of models.

Complete example of how to build an Agentic RAG architecture with Redis, Amazon Bedrock, and LlamaIndex.

Code and models for "Pano3D: A Holistic Benchmark and a Solid Baseline for 360 Depth Estimation", OmniCV Workshop @ CVPR21.

SDK for using LLM

Python toolkit for speech processing

Toward Realistic Single-View 3D Object Reconstruction with Unsupervised Learning from Multiple Images (ICCV 2021)

Easy "1-line" calling of all LLMs from OpenAI, MS Azure, AWS Bedrock, GCP Vertex, and Ollama

编程导航 2025 年 AI 开发实战新项目，基于 Spring Boot 3 + Java 21 + WxJava + Spring AI 的智能公众号管理系统，整合 ​​WxJava​​ 与 ​​Spring AI​​，实现多公众号的统一管理、​​AI 智能回复和素材管理​​。完整的后端 + React 前端全栈项目，覆盖公众号服务器配置、公众号 AI 自动回复、公众号素材管理、公众号菜单栏配置、本地开发调试微信公众号接口等功能。帮助你快速掌握公众号相关功能开发，让自己的公众号更加智能。

Deep Learning & Natural Language Processing model to generate Piano music using LSTM Neural Networks