Google Research (@google-research)

Top repositories

1

bert

TensorFlow code and pre-trained models for BERT
Python
34,874
star
2

google-research

Google Research
Jupyter Notebook
31,375
star
3

tuning_playbook

A playbook for systematically maximizing the performance of deep learning models.
22,611
star
4

vision_transformer

Jupyter Notebook
8,232
star
5

text-to-text-transfer-transformer

Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"
Python
5,589
star
6

arxiv-latex-cleaner

arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv
Python
4,245
star
7

simclr

SimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learners
Jupyter Notebook
3,743
star
8

multinerf

A Code Release for Mip-NeRF 360, Ref-NeRF, and RawNeRF
Python
3,307
star
9

football

Check out the new game server:
Python
3,183
star
10

albert

ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
Python
3,155
star
11

scenic

Scenic: A Jax Library for Computer Vision Research and Beyond
Python
2,638
star
12

electra

ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators
Python
2,211
star
13

t5x

Python
2,198
star
14

frame-interpolation

FILM: Frame Interpolation for Large Motion, In ECCV 2022.
Python
2,196
star
15

uda

Unsupervised Data Augmentation (UDA)
Python
2,131
star
16

kubric

A data generation pipeline for creating semi-realistic synthetic multi-object videos with rich annotations such as instance segmentation masks, depth maps, and optical flow.
Jupyter Notebook
2,030
star
17

pegasus

Python
1,555
star
18

dex-lang

Research language for array processing in the Haskell/ML family
Haskell
1,514
star
19

language

Shared repository for open-sourced projects from the Google AI Language team.
Python
1,492
star
20

parti

1,483
star
21

big_transfer

Official repository for the "Big Transfer (BiT): General Visual Representation Learning" paper.
Python
1,462
star
22

torchsde

Differentiable SDE solvers with GPU support and efficient sensitivity analysis.
Python
1,381
star
23

disentanglement_lib

disentanglement_lib is an open-source library for research on learning disentangled representations.
Python
1,311
star
24

FLAN

Python
1,261
star
25

multilingual-t5

Python
1,177
star
26

planet

Learning Latent Dynamics for Planning from Pixels
Python
1,134
star
27

mixmatch

Python
1,121
star
28

tapas

End-to-end neural table-text understanding models.
Python
1,049
star
29

fixmatch

A simple method to perform semi-supervised learning with limited data.
Python
1,036
star
30

morph-net

Fast & Simple Resource-Constrained Learning of Deep Network Structure
Python
1,013
star
31

robotics_transformer

Python
995
star
32

big_vision

Official codebase used to develop Vision Transformer, MLP-Mixer, LiT and more.
Jupyter Notebook
972
star
33

batch-ppo

Efficient Batched Reinforcement Learning in TensorFlow
Python
963
star
34

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.
Python
949
star
35

augmix

AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
Python
946
star
36

maxim

[CVPR 2022 Oral] Official repository for "MAXIM: Multi-Axis MLP for Image Processing". SOTA for denoising, deblurring, deraining, dehazing, and enhancement.
Python
821
star
37

seed_rl

SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference. Implements IMPALA and R2D2 algorithms in TF2 with SEED's architecture.
Python
779
star
38

deduplicate-text-datasets

Rust
750
star
39

pix2seq

Pix2Seq codebase: multi-tasks with generative modeling (autoregressive and diffusion)
Jupyter Notebook
739
star
40

noisystudent

Code for Noisy Student Training. https://arxiv.org/abs/1911.04252
Python
725
star
41

meta-dataset

A dataset of datasets for learning to learn from few examples
Python
720
star
42

lottery-ticket-hypothesis

A reimplementation of "The Lottery Ticket Hypothesis" (Frankle and Carbin) on MNIST.
Python
700
star
43

recsim

A Configurable Recommender Systems Simulation Platform
Python
697
star
44

jax3d

Python
695
star
45

nasbench

NASBench: A Neural Architecture Search Dataset and Benchmark
Python
641
star
46

circuit_training

Python
636
star
47

rliable

[NeurIPS'21 Outstanding Paper] Library for reliable evaluation on RL and ML benchmarks, even with only a handful of seeds.
Jupyter Notebook
633
star
48

long-range-arena

Long Range Arena for Benchmarking Efficient Transformers
Python
625
star
49

magvit

Official JAX implementation of MAGVIT: Masked Generative Video Transformer
Python
605
star
50

xtreme

XTREME is a benchmark for the evaluation of the cross-lingual generalization ability of pre-trained multilingual models that covers 40 typologically diverse languages and includes nine tasks.
Python
602
star
51

lasertagger

Python
599
star
52

bleurt

BLEURT is a metric for Natural Language Generation based on transfer learning.
Python
582
star
53

dreamer

Dream to Control: Learning Behaviors by Latent Imagination
Python
568
star
54

federated

A collection of Google research projects related to Federated Learning and Federated Analytics.
Python
568
star
55

sound-separation

Python
561
star
56

prompt-tuning

Original Implementation of Prompt Tuning from Lester, et al, 2021
Python
545
star
57

bigbird

Transformers for Longer Sequences
Python
518
star
58

fast-soft-sort

Fast Differentiable Sorting and Ranking
Python
515
star
59

robopianist

[CoRL '23] Dexterous piano playing with deep reinforcement learning.
Python
486
star
60

tensor2robot

Distributed machine learning infrastructure for large-scale robotics research
Python
483
star
61

batch_rl

Offline Reinforcement Learning (aka Batch Reinforcement Learning) on Atari 2600 games
Python
476
star
62

ravens

Train robotic agents to learn pick and place with deep learning for vision-based manipulation in PyBullet. Transporter Nets, CoRL 2020.
Python
468
star
63

sam

Python
463
star
64

leaf-audio

LEAF is a learnable alternative to audio features such as mel-filterbanks, that can be initialized as an approximation of mel-filterbanks, and then be trained for the task at hand, while using a very small number of parameters.
Python
446
star
65

robustness_metrics

Jupyter Notebook
442
star
66

byt5

Python
442
star
67

mint

Multi-modal Content Creation Model Training Infrastructure including the FACT model (AI Choreographer) implementation.
Python
436
star
68

vmoe

Jupyter Notebook
425
star
69

adapter-bert

Python
423
star
70

receptive_field

Compute receptive fields of your favorite convnets
Python
407
star
71

ssl_detection

Semi-supervised learning for object detection
Python
389
star
72

maxvit

[ECCV 2022] Official repository for "MaxViT: Multi-Axis Vision Transformer". SOTA foundation models for classification, detection, segmentation, image quality, and generative modeling...
Jupyter Notebook
382
star
73

pix2struct

Python
380
star
74

tf-slim

Python
359
star
75

computation-thru-dynamics

Understanding computation in artificial and biological recurrent networks through the lens of dynamical systems.
Jupyter Notebook
346
star
76

realworldrl_suite

Real-World RL Benchmark Suite
Python
330
star
77

l2p

Learning to Prompt (L2P) for Continual Learning @ CVPR22 and DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning @ ECCV22
Python
327
star
78

nerf-from-image

Shape, Pose, and Appearance from a Single Image via Bootstrapped Radiance Field Inversion
Python
317
star
79

rigl

End-to-end training of sparse deep neural networks with little-to-no performance loss.
Python
305
star
80

maskgit

Official Jax Implementation of MaskGIT
Jupyter Notebook
300
star
81

tensorflow_constrained_optimization

Python
297
star
82

python-graphs

A static analysis library for computing graph representations of Python programs suitable for use with graph neural networks.
Python
292
star
83

exoplanet-ml

Machine learning models and utilities for exoplanet science.
Python
283
star
84

task_adaptation

Python
279
star
85

tensorflow-coder

Python
272
star
86

falken

Falken provides developers with a service that allows them to train AI that can play their games
Python
250
star
87

ibc

Official implementation of Implicit Behavioral Cloning, as described in our CoRL 2021 paper, see more at https://implicitbc.github.io/
Python
243
star
88

self-organising-systems

Jupyter Notebook
236
star
89

vdm

Jupyter Notebook
227
star
90

distilling-step-by-step

Python
227
star
91

ott

Python
215
star
92

perceiver-ar

Python
207
star
93

3d-moments

Code for CVPR 2022 paper '3D Moments from Near-Duplicate Photos'
Python
204
star
94

lm-extraction-benchmark

Python
202
star
95

lag

Python
193
star
96

episodic-curiosity

Tensorflow/Keras code and trained models for Episodic Curiosity Through Reachability
Jupyter Notebook
190
star
97

nested-transformer

Nested Hierarchical Transformer https://arxiv.org/pdf/2105.12723.pdf
Jupyter Notebook
185
star
98

data-driven-advection

Jupyter Notebook
184
star
99

jaxpruner

Python
184
star
100

reassessed-imagenet

Labels and other data for the paper "Are we done with ImageNet?"
178
star