zaina-ml/ml_forge

All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.

Create your custom OpenCV pipelines using a user-friendly node editor, inspired by industry-leading interfaces! Quickly prototype your vision as you edit.

Build, train, optimize, and run computer vision models locally, from raw images to live inference. Open source, optimized for Intel XPU (CPU-only and CUDA also supported).

🤖 Interactive Machine Learning experiments: 🏋️models training + 🎨models demo

The official Roboflow Python package. Manage your datasets, models, and deployments. Roboflow has everything you need to build a computer vision application.

A python library for self-supervised learning on images.

Images to inference with no labeling (use foundation models to train supervised models).

An intuitive console agent to fine-tune AI models with little to no experience required!

Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.