YOLOv12 Underwater Object Detection is an open-source suite for underwater object detection, built on YOLOv12. It offers an end-to-end pipeline with GPU-accelerated training, customizable data augmentations, real-time inference via Gradio, and support for model export (ONNX & PyTorch).

Blender add-on to import/export BattleForge / Skylords Reborn 3D models, animations, materials, and collisions (.drs, .bmg, .ska).

Convert XGBoost models (XGBRegressor/XGBClassifier) to Excel formula expressions for spreadsheet deployment

Modular pipeline for building RAG and LLM workflows in Colab, including tokenizer/chunk/embed notebooks and CoreML model exporters for iOS. Part of the NoesisNoema project.

A standalone version of the next PyTorch ONNX exporter

Machine Learning model optimizer and exporter for embedded systems and mobile platforms

JAX/Flax physics-informed neural network with jax2tf export — benchmark JAX vs PyTorch vs TensorFlow

A tool to jsonify some sklearn and xgboost models. A high level serialization that works across programming languages. Used for mllite tests.

A lightweight Few-Shot Image Classifier built with PyTorch, capable of recognizing new classes from just a few examples using prototype-based learning. Designed for easy model export and integration.