Composer alternatives for AI agents.

Deep Learning for humans

High-level library to help with training and evaluating neural networks in PyTorch flexibly and transparently.

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

Ultralytics YOLOv5 in PyTorch > ONNX > CoreML > TFLite

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Code Repository for Machine Learning with PyTorch and Scikit-Learn

Rust bindings for the C++ api of PyTorch.

🐍 Geometric Computer Vision Library for Spatial AI

Deep universal probabilistic programming with Python and PyTorch

TensorFlow-based neural network library

BertViz: Visualize Attention in Transformer Models

Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.

Probabilistic time series modeling in Python

Machine Learning and Agentic AI Resources, Practice and Research