機械学習 · GitHub

🧑‍🏫 注釈を横に並べて読める、深層学習論文の実装とチュートリアル 60 本以上 📝。Transformer（オリジナル、XL、Switch、Feedback、ViT など）、オプティマイザ（Adam、AdaBelief、Sophia など）、GAN（CycleGAN、StyleGAN2 など）、🎮 強化学習（PPO、DQN）、CapsNet、蒸留などを収録 🧠

C++ コアと Python で拡張可能な 50 以上のノードを備えた高性能 AI パイプラインエンジン。13 以上のモデルプロバイダー、8 以上のベクトルデータベース、エージェントオーケストレーションに対応し、すべてを IDE から LLM ワークフローの構築、デバッグ、スケーリングに利用できます。VS Code 拡張機能、TypeScript/Python SDK、Docker デプロイにも対応しています。

• Rocket Builder - Drag, connect, and configure nodes visually, no boilerplate. Real-time observability tracks token usage, LLM calls, latency, and execution. Pipelines are portable JSON, version-controllable, shareable, and runnable anywhere.
• High-Performance C++ Runtime - Native multithreading purpose-built for the throughput demands of AI and data workloads. No bottlenecks, no compromises for production scale.

Vision-Centric BEV Perception: A Survey

A simple face detect and alignment method, which is easy and stable.

者也 - 知乎 倒立的文字 汉字验证码识别程序

An optical music recognition (OMR) system. Converts sheet music to a machine-readable version.

PyTorch DDPM implementation

This project analyzes Tennis players in a video to measure their speed, ball shot speed and number of shots. This project will detect players and the tennis ball using YOLO and also utilizes CNNs to extract court keypoints. This hands on project is perfect for polishing your machine learning, and computer vision skills.

Feature exploration for supervised learning

This projects aims in detection of video deepfakes using deep learning techniques like RestNext and LSTM. We have achived deepfake detection by using transfer learning where the pretrained RestNext CNN is used to obtain a feature vector, further the LSTM layer is trained using the features. For more details follow the documentaion.