ktx is an executable context layer for data and analytics agents 🐙 Allow Claude Code, Codex, or other AI agents to query data accurately and with full context of your company

Phare Benchmark Runner

🐢 Open-Source Evaluation & Testing library for LLM Agents

A playbook for systematically maximizing the performance of deep learning models.

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

🐍 Geometric Computer Vision Library for Spatial AI

Code for the Convolutional Vision Transformer (ConViT)

OpenMMLab FewShot Learning Toolbox and Benchmark

Leaderboard, taxonomy, and curated list of few-shot object detection papers.

Alignment Attention Fusion framework for Few-Shot Object Detection

LTeX: Grammar/spell checker 🔍✔️ for VS Code using LanguageTool with support for LaTeX 🎓, Markdown 📝, and others

📄 A paper list of Few-shot Object Detection.

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

Cockpit: A Practical Debugging Tool for Training Deep Neural Networks

FewX is an open-source toolbox on top of Detectron2 for data-limited instance-level recognition tasks.

A clean and simple data loading library for Continual Learning

Datasets, Transforms and Models specific to Computer Vision

Few-shot detection for visual categories

Neural network graphs and training metrics for PyTorch, Tensorflow, and Keras.

End-to-End Object Detection with Transformers

3D Ken Burns effect and dolly zoom from single image.

Animation engine for explanatory math videos

A PyTorch library entirely dedicated to neural differential equations, implicit models and related numerical methods

🧀 Pytorch code for the Fromage optimiser.

an implementation of 3D Ken Burns Effect from a Single Image using PyTorch