Google Research

A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in Python using Scikit-Learn, Keras and TensorFlow 2.

PyTorch code and models for the DINOv2 self-supervised learning method.

Multi-Joint dynamics with Contact. A general purpose physics simulator.

Massively parallel rigidbody physics simulation on accelerator hardware.

VPoser: Variational Human Pose Prior

Data preparation and loader for AMASS

[ICML 2020] PyTorch Code for "One Policy to Control Them All: Shared Modular Policies for Agent-Agnostic Control"

End-to-end Recovery of Human Shape and Pose with tensorflow 2.0

multiOn Challenge Code