google-research/python-graphs

Stars
325
Rank 129,350 (Top 3 %)
Language
Python
License
Apache License 2.0
Created over 3 years ago
Updated over 1 year ago

google-research/python-graphs

google-research

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

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

python_graphs

This package is for computing graph representations of Python programs for machine learning applications. It includes the following modules:

control_flow For computing control flow graphs statically from Python programs.
data_flow For computing data flow analyses of Python programs.
program_graph For computing graphs statically to represent arbitrary Python programs or functions.
cyclomatic_complexity For computing the cyclomatic complexity of a Python function.

Installation

To install python_graphs with pip, run: pip install python_graphs.

To install python_graphs from source, run: python setup.py develop.

Common Tasks

Generate a control flow graph from a function fn:

from python_graphs import control_flow
graph = control_flow.get_control_flow_graph(fn)

Generate a program graph from a function fn:

from python_graphs import program_graph
graph = program_graph.get_program_graph(fn)

Compute the cyclomatic complexity of a function fn:

from python_graphs import control_flow
from python_graphs import cyclomatic_complexity
graph = control_flow.get_control_flow_graph(fn)
value = cyclomatic_complexity.cyclomatic_complexity(graph)

This is not an officially supported Google product.

bert

TensorFlow code and pre-trained models for BERT

google-research

Google Research

Jupyter Notebook

tuning_playbook

A playbook for systematically maximizing the performance of deep learning models.

vision_transformer

Jupyter Notebook

text-to-text-transfer-transformer

Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"

arxiv-latex-cleaner

arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

simclr

SimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learners

Jupyter Notebook

multinerf

A Code Release for Mip-NeRF 360, Ref-NeRF, and RawNeRF

timesfm

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.

scenic

Scenic: A Jax Library for Computer Vision Research and Beyond

football

Check out the new game server:

albert

ALBERT: A Lite BERT for Self-supervised Learning of Language Representations

frame-interpolation

FILM: Frame Interpolation for Large Motion, In ECCV 2022.

t5x

electra

ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators

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

big_vision

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

Jupyter Notebook

uda

Unsupervised Data Augmentation (UDA)

language

Shared repository for open-sourced projects from the Google AI Language team.

pegasus

dex-lang

Research language for array processing in the Haskell/ML family

torchsde

Differentiable SDE solvers with GPU support and efficient sensitivity analysis.

parti

big_transfer

Official repository for the "Big Transfer (BiT): General Visual Representation Learning" paper.

FLAN

robotics_transformer

disentanglement_lib

disentanglement_lib is an open-source library for research on learning disentangled representations.

multilingual-t5

circuit_training

tapas

End-to-end neural table-text understanding models.

planet

Learning Latent Dynamics for Planning from Pixels

mixmatch

deduplicate-text-datasets

fixmatch

A simple method to perform semi-supervised learning with limited data.

morph-net

Fast & Simple Resource-Constrained Learning of Deep Network Structure

maxim

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

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.

batch-ppo

Efficient Batched Reinforcement Learning in TensorFlow

augmix

AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty

magvit

Official JAX implementation of MAGVIT: Masked Generative Video Transformer

pix2seq

Pix2Seq codebase: multi-tasks with generative modeling (autoregressive and diffusion)

Jupyter Notebook

seed_rl

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

meta-dataset

A dataset of datasets for learning to learn from few examples

Jupyter Notebook

noisystudent

Code for Noisy Student Training. https://arxiv.org/abs/1911.04252

rliable

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

Jupyter Notebook

recsim

A Configurable Recommender Systems Simulation Platform

jax3d

long-range-arena

Long Range Arena for Benchmarking Efficient Transformers

lottery-ticket-hypothesis

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

federated

A collection of Google research projects related to Federated Learning and Federated Analytics.

bleurt

BLEURT is a metric for Natural Language Generation based on transfer learning.

prompt-tuning

Original Implementation of Prompt Tuning from Lester, et al, 2021

nasbench

NASBench: A Neural Architecture Search Dataset and Benchmark

neuralgcm

Hybrid ML + physics model of the Earth's atmosphere

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.

lasertagger

sound-separation

pix2struct

vmoe

Jupyter Notebook

dreamer

Dream to Control: Learning Behaviors by Latent Imagination

robopianist

[CoRL '23] Dexterous piano playing with deep reinforcement learning.

omniglue

Code release for CVPR'24 submission 'OmniGlue'

fast-soft-sort

Fast Differentiable Sorting and Ranking

ravens

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

sam

batch_rl

Offline Reinforcement Learning (aka Batch Reinforcement Learning) on Atari 2600 games

bigbird

Transformers for Longer Sequences

tensor2robot

Distributed machine learning infrastructure for large-scale robotics research

byt5

adapter-bert

mint

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

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.

robustness_metrics

Jupyter Notebook

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

receptive_field

Compute receptive fields of your favorite convnets

maskgit

Official Jax Implementation of MaskGIT

Jupyter Notebook

weatherbench2

A benchmark for the next generation of data-driven global weather models.

l2p

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

distilling-step-by-step

ssl_detection

Semi-supervised learning for object detection

nerf-from-image

Shape, Pose, and Appearance from a Single Image via Bootstrapped Radiance Field Inversion

computation-thru-dynamics

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

Jupyter Notebook

tf-slim

realworldrl_suite

Real-World RL Benchmark Suite

rigl

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

task_adaptation

self-organising-systems

Jupyter Notebook

ibc

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

tensorflow_constrained_optimization

syn-rep-learn

Learning from synthetic data - code and models

arco-era5

Recipes for reproducing Analysis-Ready & Cloud Optimized (ARCO) ERA5 datasets.

vdm

Jupyter Notebook

rlds

Jupyter Notebook

exoplanet-ml

Machine learning models and utilities for exoplanet science.

retvec

RETVec is an efficient, multilingual, and adversarially-robust text vectorizer.

Jupyter Notebook

sparf

This is the official code release for SPARF: Neural Radiance Fields from Sparse and Noisy Poses [CVPR 2023-Highlight]

tensorflow-coder

lm-extraction-benchmark

language-table

Suite of human-collected datasets and a multi-task continuous control benchmark for open vocabulary visuolinguomotor learning.

Jupyter Notebook

falken

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