Scenic: A Jax Library for Computer Vision and Beyond

Overview

Scenic

Scenic is a codebase with a focus on research around attention-based models for computer vision. Scenic has been successfully used to develop classification, segmentation, and detection models for multiple modalities including images, video, audio, and multimodal combinations of them.

More precisely, Scenic is a (i) set of shared light-weight libraries solving tasks commonly encountered tasks when training large-scale (i.e. multi-device, multi-host) vision models; and (ii) a number of projects containing fully fleshed out problem-specific training and evaluation loops using these libraries.

Scenic is developed in JAX and uses Flax.

What we offer

Among others Scenic provides

  • Boilerplate code for launching experiments, summary writing, logging, profiling, etc;
  • Optimized training and evaluation loops, losses, metrics, bi-partite matchers, etc;
  • Input-pipelines for popular vision datasets;
  • Baseline models, including strong non-attentional baselines.

Papers using Scenic

Scenic can be used to reproduce the results from the following papers, which were either developed using Scenic, or have been reimplemented in Scenic:

Philosophy

Scenic aims to facilitate rapid prototyping of large-scale vision models. To keep the code simple to understand and extend we prefer forking and copy-pasting over adding complexity or increasing abstraction. Only when functionality proves to be widely useful across many models and tasks it may be upstreamed to Scenic's shared libraries.

Code structure

Shared libraries provided by Scenic are split into:

  • dataset_lib: Implements IO pipelines for loading and pre-processing data for common Computer Vision tasks and benchmarks. All pipelines are designed to be scalable and support multi-host and multi-device setups, taking care of dividing data among multiple hosts, incomplete batches, caching, pre-fetching, etc.
  • model_lib: Provides (i) several abstract model interfaces (e.g. ClassificationModel or SegmentationModel in model_lib.base_models) with task-specific losses and metrics; (ii) neural network layers in model_lib.layers, focusing on efficient implementation of attention and transfomer layers; and (iii) accelerator-friedly implementations of bipartite matching algorithms in model_lib.matchers.
  • train_lib: Provides tools for constructing training loops and implements several example trainers (classification trainer and segmentation trainer).
  • common_lib: Utilities that do not belong anywhere else.

Projects

Models built on top of Scenic exist as separate projects. Model-specific code such as configs, layers, losses, network architectures, or training and evaluation loops exist as separate projects.

Common baselines such as a ResNet or a Visual Transformer (ViT) are implemented in the projects/baselines project. Forking this directory is a good starting point for new projects.

There is no one-fits-all recipe for how much code should be re-used by projects. Projects can fall anywhere on the wide spectrum of code re-use: from defining new configs for an existing model to redefining models, training loop, logging, etc.

Getting started

  • See projects/baselines/README.md for a walk-through baseline models and instructions on how to run the code.
  • If you would like to to contribute to Scenic, please check out the Philisophy, Code structure and Contributing sections. Should your contribution be a part of the shared libraries, please send us a pull request!

Quick start

Download the code from GitHub

git clone https://github.com/google-research/scenic.git
cd scenic
pip install .

and run training for ViT on ImageNet:

python main.py -- \
  --config=projects/baselines/configs/imagenet/imagenet_vit_config.py \
  --workdir=./

Disclaimer: This is not an official Google product.

Owner
Google Research
Google Research
A Python Package for Portfolio Optimization using the Critical Line Algorithm

PyCLA A Python Package for Portfolio Optimization using the Critical Line Algorithm Getting started To use PyCLA, clone the repo and install the requi

19 Oct 11, 2022
A PyTorch Lightning Callback for pushing models to the Hugging Face Hub 🤗⚡️

hf-hub-lightning A callback for pushing lightning models to the Hugging Face Hub. Note: I made this package for myself, mostly...if folks seem to be i

Nathan Raw 27 Dec 14, 2022
Official implementation of Self-supervised Image-to-text and Text-to-image Synthesis

Self-supervised Image-to-text and Text-to-image Synthesis This is the official implementation of Self-supervised Image-to-text and Text-to-image Synth

6 Jul 31, 2022
A PyTorch implementation of EfficientDet.

A PyTorch impl of EfficientDet faithful to the original Google impl w/ ported weights

Ross Wightman 1.4k Jan 07, 2023
code for our ECCV-2020 paper: Self-supervised Video Representation Learning by Pace Prediction

Video_Pace This repository contains the code for the following paper: Jiangliu Wang, Jianbo Jiao and Yunhui Liu, "Self-Supervised Video Representation

Jiangliu Wang 95 Dec 14, 2022
Differentiable Annealed Importance Sampling (DAIS)

Differentiable Annealed Importance Sampling (DAIS) This repository contains the code to reproduce the DAIS results from the paper Differentiable Annea

Guodong Zhang 6 Dec 26, 2021
Image De-raining Using a Conditional Generative Adversarial Network

Image De-raining Using a Conditional Generative Adversarial Network [Paper Link] [Project Page] He Zhang, Vishwanath Sindagi, Vishal M. Patel In this

He Zhang 216 Dec 18, 2022
source code for 'Finding Valid Adjustments under Non-ignorability with Minimal DAG Knowledge' by A. Shah, K. Shanmugam, K. Ahuja

Source code for "Finding Valid Adjustments under Non-ignorability with Minimal DAG Knowledge" Reference: Abhin Shah, Karthikeyan Shanmugam, Kartik Ahu

Abhin Shah 1 Jun 03, 2022
[CVPR2021] Look before you leap: learning landmark features for one-stage visual grounding.

LBYL-Net This repo implements paper Look Before You Leap: Learning Landmark Features For One-Stage Visual Grounding CVPR 2021. Getting Started Prerequ

SVIP Lab 45 Dec 12, 2022
This is a official repository of SimViT.

SimViT This is a official repository of SimViT. We will open our models and codes about object detection and semantic segmentation soon. Our code refe

ligang 57 Dec 15, 2022
Adapter-BERT: Parameter-Efficient Transfer Learning for NLP.

Adapter-BERT: Parameter-Efficient Transfer Learning for NLP.

Google Research 340 Jan 03, 2023
Towards Rolling Shutter Correction and Deblurring in Dynamic Scenes (CVPR2021)

RSCD (BS-RSCD & JCD) Towards Rolling Shutter Correction and Deblurring in Dynamic Scenes (CVPR2021) by Zhihang Zhong, Yinqiang Zheng, Imari Sato We co

81 Dec 15, 2022
A simple command line tool for text to image generation, using OpenAI's CLIP and a BigGAN.

Ryan Murdock has done it again, combining OpenAI's CLIP and the generator from a BigGAN! This repository wraps up his work so it is easily accessible to anyone who owns a GPU.

Phil Wang 2.3k Jan 09, 2023
Simple reference implementation of GraphSAGE.

Reference PyTorch GraphSAGE Implementation Author: William L. Hamilton Basic reference PyTorch implementation of GraphSAGE. This reference implementat

William L Hamilton 861 Jan 06, 2023
[ICML 2021] A fast algorithm for fitting robust decision trees.

GROOT: Growing Robust Trees Growing Robust Trees (GROOT) is an algorithm that fits binary classification decision trees such that they are robust agai

Cyber Analytics Lab 17 Nov 21, 2022
Improving Query Representations for DenseRetrieval with Pseudo Relevance Feedback:A Reproducibility Study.

APR The repo for the paper Improving Query Representations for DenseRetrieval with Pseudo Relevance Feedback:A Reproducibility Study. Environment setu

ielab 8 Nov 26, 2022
3ds-Ghidra-Scripts - Ghidra scripts to help with 3ds reverse engineering

3ds Ghidra Scripts These are ghidra scripts to help with 3ds reverse engineering

Zak 7 May 23, 2022
A minimalist environment for decision-making in autonomous driving

highway-env A collection of environments for autonomous driving and tactical decision-making tasks An episode of one of the environments available in

Edouard Leurent 1.6k Jan 07, 2023
Arabic Car License Recognition. A solution to the kaggle competition Machathon 3.0.

Transformers Arabic licence plate recognition 🚗 Solution to the kaggle competition Machathon 3.0. Ranked in the top 6️⃣ at the final evaluation phase

Noran Hany 17 Dec 04, 2022
My solutions for Stanford University course CS224W: Machine Learning with Graphs Fall 2021 colabs (GNN, GAT, GraphSAGE, GCN)

machine-learning-with-graphs My solutions for Stanford University course CS224W: Machine Learning with Graphs Fall 2021 colabs Course materials can be

Marko Njegomir 7 Dec 14, 2022