Apprentissage automatique · GitHub

🧑‍🏫 Plus de 60 implémentations et tutoriels d’articles d’apprentissage profond, avec des notes côte à côte 📝 ; notamment les transformers (original, XL, Switch, Feedback, ViT, ...), les optimiseurs (Adam, AdaBelief, Sophia, ...), les GAN (CycleGAN, StyleGAN2, ...), 🎮 l’apprentissage par renforcement (PPO, DQN), CapsNet, la distillation, ... 🧠

Moteur de pipelines d’IA haute performance doté d’un cœur C++ et de plus de 50 nœuds extensibles en Python. Créez, déboguez et faites évoluer des workflows LLM depuis votre IDE, avec plus de 13 fournisseurs de modèles, plus de 8 bases de données vectorielles et l’orchestration d’agents. Inclut une extension VS Code, des SDK TypeScript/Python et le déploiement avec Docker.

• 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.