Google Research

This repository contains code released by Google Research.

All datasets in this repository are released under the CC BY 4.0 International license, which can be found here: https://creativecommons.org/licenses/by/4.0/legalcode. All source files in this repository are released under the Apache 2.0 license, the text of which can be found in the LICENSE file.

Because the repo is large, we recommend you download only the subdirectory of interest:

Use GitHub editor to open the project. To open the editor change the url from github.com to github.dev in the address bar.
In the left navigation panel, right-click on the folder of interest and select download.

If you'd like to submit a pull request, you'll need to clone the repository; we recommend making a shallow clone (without history).

git clone [email protected]:google-research/google-research.git --depth=1

Disclaimer: This is not an official Google product.

Updated in 2023.

Google Research's Projects

clevr_robot_env

CLEVR-Robot: a reinforcement learning environment combining vision, language and control.

compressive-visual-representations

Tensorflow 2 implementations of the C-SimCLR and C-BYOL self-supervised visual representation methods from "Compressive Visual Representations" (NeurIPS 2021)

computation-thru-dynamics

Understanding computation in artificial and biological recurrent networks through the lens of dynamical systems.

corenet

CoReNet is a technique for joint multi-object 3D reconstruction from a single RGB image.

crest

Repo for CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning

dads

Code for 'Dynamics-Aware Unsupervised Discovery of Skills' (DADS). Enables skill discovery without supervision, which can be combined with model-based control.

dataclass_array

Dataclasses manipulated as numpy arrays (with batching, reshape, slicing,...)

dataset_grouper

Libraries for efficient and scalable group-structured dataset pipelines.

deeplab2

DeepLab2 is a TensorFlow library for deep labeling, aiming to provide a unified and state-of-the-art TensorFlow codebase for dense pixel labeling tasks.