Repository files navigation

Below we share, in reverse chronological order, the updates and new releases in VISSL. All VISSL releases are availablehere.

• [Feb 2022]: ReleasingSEER 10B parameters modelimplementation and model weights.
• [Feb 2022]: Releasingimplementation of Fairness Benchmarks for computer vision models proposed inthe paper.
• [Jan 2022]:Implementation for Geolocalization test (gps prediction for an image) released in VISSL.
• [Jan 2022]: AddBEiT transformerimplementation andClassyVision ViT.
• [Nov 2021]:Vissl Release 0.1.6 We have released a new version of VISSL. Please see ourrelease notes for more information.
• [Oct 2021]:AugLy data augmentations support introduced in thiscommit.
• [Oct 2021]:XCiT: Cross-Covariance Image Transformers code released in thiscommit.
• [Sept 2021]: VISSL master branch renamed to main in thisPR in VISSL.
• [August 2021]: Instance Retrieval benchmark implemented andavailable in VISSL.
• [July 2021]:Fully Sharded Data Parallel integrated in VISSL and announced inblog.
• [May 2021]:DINO: Emerging Properties in Self-Supervised Vision Transformers code released.
• [May 2021]: VISSL relicensed underMIT License.
• [May 2021]:Barlow Twins: Self-Supervised Learning via Redundancy Reduction code released.
• [April 2021]:ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases code released.
• [March 2021]: Added most benchmark datasets used inVTAB andCLIP benchmark tasks.
• [February 2021]: AddedVision Transformers (ViT) backbone andtraining self-supervision with ViT.
• [January 2021]: VISSL v0.1.5 released.

VISSL is a computerVIsion library for state-of-the-artSelf-SupervisedLearning research withPyTorch. VISSL aims to accelerate research cycle in self-supervised learning: from designing a new self-supervised task to evaluating the learned representations. Key features include:

• Reproducible implementation of SOTA in Self-Supervision: All existing SOTA in Self-Supervision are implemented -SwAV,SimCLR,MoCo(v2),PIRL,NPID,NPID++,DeepClusterV2,ClusterFit,RotNet,Jigsaw. Also supports supervised trainings.

• Benchmark suite: Variety of benchmarks tasks includinglinear image classification (places205, imagenet1k, voc07, food, CLEVR, dsprites, UCF101, stanford cars and many more),full finetuning,semi-supervised benchmark,nearest neighbor benchmark,object detection (Pascal VOC and COCO).

• Ease of Usability: easy to use using yaml configuration system based onHydra.

• Modular: Easy to design new tasks and reuse the existing components from other tasks (objective functions, model trunk and heads, data transforms, etc.). The modular components are simpledrop-in replacements in yaml config files.

• Scalability: Easy to train model on 1-gpu, multi-gpu and multi-node. Several components for large scale trainings provided as simple config file plugs:Activation checkpointing,ZeRO,FP16,LARC, Stateful data sampler, data class to handle invalid images, large model backbones likeRegNets, etc.

• Model Zoo: Over60 pre-trained self-supervised model weights.

SeeINSTALL.md.

Install VISSL by following theinstallation instructions.After installation, please seeGetting Started with VISSL and theColab Notebook to learn about basic usage.

Learn more about VISSL at ourdocumentation. And see theprojects/ for some projects built on top of VISSL.

Get started with VISSL by trying one of theColab tutorial notebooks.

• Train SimCLR on 1-gpu
• Extracting Features from a pretrained model
• Benchmark task: Full finetuning on ImageNet-1K
• Benchmark task: Linear image classification on ImageNet-1K
• Large scale training (fp16, LARC, ZeRO)
• Using a pre-trained model in inference mode

We provide a large set of baseline results and trained models available for download in theVISSL Model Zoo.

VISSL is written and maintained by the Facebook AI Research.

We welcome new contributions to VISSL and we will be actively maintaining this library! Please refer toCONTRIBUTING.md for full instructions on how to run the code, tests and linter, and submit your pull requests.

VISSL is released underMIT license.

If you find VISSL useful in your research or wish to refer to the baseline results published in theModel Zoo, please use the following BibTeX entry.

@misc{goyal2021vissl,author ={Priya Goyal and Quentin Duval and Jeremy Reizenstein and Matthew Leavitt and Min Xu and                  Benjamin Lefaudeux and Mannat Singh and Vinicius Reis and Mathilde Caron and Piotr Bojanowski and                  Armand Joulin and Ishan Misra},title ={VISSL},howpublished ={\url{https://github.com/facebookresearch/vissl}},year ={2021}}