AI 开源项目榜。
HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation
This SDK is now deprecated, use the new unified Google GenAI SDK.
PPT image-first skill for Codex/Claude Code/Opencode CLI
An introductory series to Reinforcement Learning (RL) with comprehensive step-by-step tutorials.
Awesome list for research on CLIP (Contrastive Language-Image Pre-Training).
Best practice TTS based on BERT and VITS with some Natural Speech Features Of Microsoft; Support ONNX streaming out!
Classification models trained on ImageNet. Keras.
An MCP server that autonomously evaluates web applications.
Chinese safety prompts for evaluating and improving the safety of LLMs. 中文安全prompts，用于评估和提升大模型的安全性。
A generative and self-guided robotic agent that endlessly propose and master new skills.
Raspberry Pi guitar pedal using neural networks to emulate real amps and effects.
[NeurIPS 2023] Official Code for "SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation"
FeatherCNN is a high performance inference engine for convolutional neural networks.
AI Captcha Bypass
🔒 Enterprise-grade API gateway that helps you monitor and impose cost or rate limits per API key. Get fine-grained access control and monitoring per user, application, or environment. Supports OpenAI, Azure OpenAI, Anthropic, vLLM, and open-source LLMs.
Training a humanoid robot for locomotion using Reinforcement Learning
Taranis AI is an advanced Open-Source Intelligence (OSINT) tool, leveraging Artificial Intelligence to revolutionize information gathering and situational analysis.
Entity and Relation Extraction Based on TensorFlow and BERT. 基于TensorFlow和BERT的管道式实体及关系抽取，2019语言与智能技术竞赛信息抽取任务解决方案。Schema based Knowledge Extraction, SKE 2019
Kimi-VL: Mixture-of-Experts Vision-Language Model for Multimodal Reasoning, Long-Context Understanding, and Strong Agent Capabilities
整理一些书籍 ,包含 C&C++ 、git 、Java、Keras 、Linux 、NLP 、Python 、Scala 、TensorFlow 、大数据 、推荐系统、数据库、数据挖掘 、机器学习 、深度学习 、算法等。
AdvancedEAST is an algorithm used for Scene image text detect, which is primarily based on EAST, and the significant improvement was also made, which make long text predictions more accurate.https://github.com/huoyijie/raspberrypi-car
A tiny library for coding with large language models.
Testsigma is a quality intelligence platform for AI-first engineering teams. AI made developers faster. More code ships, more surface area needs testing, and coverage gaps open faster than teams can close them.
Lab materials for the Full Stack Deep Learning Course
Stable Diffusion in Blender
Write Model Context Protocol servers in few lines of go code. Docs at https://mcpgolang.com . Created by https://metoro.io
Distribute and run AI workloads on Kubernetes magically in Python, like PyTorch for ML infra.
Visual AI workflow automation platform
Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE)
基于CNN训练的一套 "端到端" 的验证码识别模型，使用深度学习+训练数据+大量计算力，纯数字识别率高达 99.99%，数字+字母识别率 96%