Contents Menu Expand Light mode Dark mode Auto light/dark, in light mode Auto light/dark, in dark mode Skip to content
Interested in training your own vision foundation model? Check out LightlyTrain!
LightlySSL 1.6.1 documentation
Light Logo Dark Logo
lightly-ai/lightly

Getting Started

  • Main Concepts
  • Installation
  • Command-line tool
  • Self-supervised learning

World Models

  • LeWM
  • Train a World Model and Plan with It

Advanced

  • Advanced Concepts in Self-Supervised Learning
  • Distributed Training
  • Benchmarks

Tutorials

  • Tutorial 1: Structure Your Input
  • Tutorial 2: Train MoCo on CIFAR-10
  • Tutorial 3: Train SimCLR on Clothing
  • Tutorial 4: Train SimSiam on Satellite Images
  • Tutorial 5: Custom Augmentations
  • Tutorial 6: Pre-train a Detectron2 Backbone with Lightly
  • Tutorial 7: Finetuning Lightly Checkpoints
  • Tutorial 8: Using timm Models as Backbones

Examples

  • Models
    • AIM
    • Barlow Twins
    • BYOL
    • CAPI
    • DCL & DCLW
    • DetConS
    • DenseCL
    • DINO
    • DINOv2
    • FastSiam
    • FroSSL
    • iBOT
    • LeJEPA
    • MAE
    • MMCR
    • MSN
    • MoCo
    • NNCLR
    • Pixio
    • PMSN
    • SimCLR
    • SimMIM
    • SimSiam
    • SMoG
    • SwaV
    • SwaV Queue
    • TiCo
    • VICReg
    • VICRegL

Python API

  • lightly
  • lightly.cli
  • .core
  • lightly.data
  • lightly.loss
  • lightly.models
  • lightly.models.utils
  • lightly.transforms
  • lightly.utils

On-Premise

  • LightlyOne Worker
Back to top
Copyright © 2020-2026, Lightly AG
Made with Sphinx and @pradyunsg's Furo