Lightly

Refresh docs and more API helpers

Docs
- jwuphysics noticed and fixed some typos in the docs, thanks a lot!
- MalteEbner found some more and fixed them too 🙂

Support for role based access to S3 from ApiWorkflowClient
- With 841 we added helpers to configure a Lightly dataset with delegated access rules.
- 847 added the necessary documentation

Models
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction, 2021](https://arxiv.org/abs/2103.03230)
- [Bootstrap your own latent: A new approach to self-supervised Learning, 2020](https://arxiv.org/abs/2006.07733)
- [DCL: Decoupled Contrastive Learning, 2021](https://arxiv.org/abs/2110.06848)
- [DINO: Emerging Properties in Self-Supervised Vision Transformers, 2021](https://arxiv.org/abs/2104.14294)
- [MAE: Masked Autoencoders Are Scalable Vision Learners, 2021](https://arxiv.org/abs/2111.06377 )
- [MoCo: Momentum Contrast for Unsupervised Visual Representation Learning, 2019](https://arxiv.org/abs/1911.05722)
- [NNCLR: Nearest-Neighbor Contrastive Learning of Visual Representations, 2021](https://arxiv.org/pdf/2104.14548.pdf)
- [SimCLR: A Simple Framework for Contrastive Learning of Visual Representations, 2020](https://arxiv.org/abs/2002.05709)
- [SimSiam: Exploring Simple Siamese Representation Learning, 2020](https://arxiv.org/abs/2011.10566)
- [SwAV: Unsupervised Learning of Visual Features by Contrasting Cluster Assignments, M. Caron, 2020](https://arxiv.org/abs/2006.09882)

Masked Autoencoders Examples
We added [examples for the MAE model](https://docs.lightly.ai/examples/mae.html)

Docs
- We added [docs for the collapse detection helper](https://docs.lightly.ai/getting_started/advanced.html#monitoring-embedding-quality)
- We added [docs for plotting positive and negative example images](https://docs.lightly.ai/getting_started/advanced.html#previewing-augmentations)

Models
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction, 2021](https://arxiv.org/abs/2103.03230)
- [Bootstrap your own latent: A new approach to self-supervised Learning, 2020](https://arxiv.org/abs/2006.07733)
- [DCL: Decoupled Contrastive Learning, 2021](https://arxiv.org/abs/2110.06848)
- [DINO: Emerging Properties in Self-Supervised Vision Transformers, 2021](https://arxiv.org/abs/2104.14294)
- [MAE: Masked Autoencoders Are Scalable Vision Learners, 2021](https://arxiv.org/abs/2111.06377 )
- [MoCo: Momentum Contrast for Unsupervised Visual Representation Learning, 2019](https://arxiv.org/abs/1911.05722)
- [NNCLR: Nearest-Neighbor Contrastive Learning of Visual Representations, 2021](https://arxiv.org/pdf/2104.14548.pdf)
- [SimCLR: A Simple Framework for Contrastive Learning of Visual Representations, 2020](https://arxiv.org/abs/2002.05709)
- [SimSiam: Exploring Simple Siamese Representation Learning, 2020](https://arxiv.org/abs/2011.10566)
- [SwAV: Unsupervised Learning of Visual Features by Contrasting Cluster Assignments, M. Caron, 2020](https://arxiv.org/abs/2006.09882)

Masked Autoencoders
We implemented the paper **Masked Autoencoders Are Scalable Vision Learners**. https://arxiv.org/abs/2111.06377 is suggesting that a masked auto-encoder (similar to pre-training on NLP) works very well as a pretext task for self-supervised learning. See https://github.com/lightly-ai/lightly/issues/721 for more details. Thanks to Atharva-Phatak for helping us figure out a good implementation method.

Collapse detection helper for SimSiam
We added a helper for detecting a collapsing SimSiam network. See https://ar5iv.labs.arxiv.org/html/2011.10566#S4.SS1 for more details.

Plot positive and negative example images
We added a helper to plot positive and negative example images, which also allows seeing what the augmentations do. See https://github.com/lightly-ai/lightly/pull/818 for more details.

Models
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction, 2021](https://arxiv.org/abs/2103.03230)
- [Bootstrap your own latent: A new approach to self-supervised Learning, 2020](https://arxiv.org/abs/2006.07733)
- [DCL: Decoupled Contrastive Learning, 2021](https://arxiv.org/abs/2110.06848)
- [DINO: Emerging Properties in Self-Supervised Vision Transformers, 2021](https://arxiv.org/abs/2104.14294)
- [MAE: Masked Autoencoders Are Scalable Vision Learners, 2021](https://arxiv.org/abs/2111.06377 )
- [MoCo: Momentum Contrast for Unsupervised Visual Representation Learning, 2019](https://arxiv.org/abs/1911.05722)
- [NNCLR: Nearest-Neighbor Contrastive Learning of Visual Representations, 2021](https://arxiv.org/pdf/2104.14548.pdf)
- [SimCLR: A Simple Framework for Contrastive Learning of Visual Representations, 2020](https://arxiv.org/abs/2002.05709)
- [SimSiam: Exploring Simple Siamese Representation Learning, 2020](https://arxiv.org/abs/2011.10566)
- [SwAV: Unsupervised Learning of Visual Features by Contrasting Cluster Assignments, M. Caron, 2020](https://arxiv.org/abs/2006.09882)

Video Dataset initialisation speedup
When initialising a `LightlyDataset` on a directory with videos, all frames in all videos have to be counted to know the number of frames in the dataset and their filenames. This process now uses multihreading over videos and can thus be much faster.
Video Dataset initialisation bugfix
We fixed a bug that the number of frames was estimated wrongly based on the length of the video when using the pyav backend.
Video Dataset initialisation progress bar
When initialising the video dataset, a progress bar over the videos is shown. This is helpful information for datasets with many videos.

Models
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction, 2021](https://arxiv.org/abs/2103.03230)
- [Bootstrap your own latent: A new approach to self-supervised Learning, 2020](https://arxiv.org/abs/2006.07733)
- [DCL: Decoupled Contrastive Learning, 2021](https://arxiv.org/abs/2110.06848)
- [DINO: Emerging Properties in Self-Supervised Vision Transformers, 2021](https://arxiv.org/abs/2104.14294)
- [MoCo: Momentum Contrast for Unsupervised Visual Representation Learning, 2019](https://arxiv.org/abs/1911.05722)
- [NNCLR: Nearest-Neighbor Contrastive Learning of Visual Representations, 2021](https://arxiv.org/pdf/2104.14548.pdf)
- [SimCLR: A Simple Framework for Contrastive Learning of Visual Representations, 2020](https://arxiv.org/abs/2002.05709)
- [SimSiam: Exploring Simple Siamese Representation Learning, 2020](https://arxiv.org/abs/2011.10566)
- [SwAV: Unsupervised Learning of Visual Features by Contrasting Cluster Assignments, M. Caron, 2020](https://arxiv.org/abs/2006.09882)

Decoupled Contrastive Learning
We have implemented the Decoupled Contrastive Learning (DCL) loss. It allows faster training with smaller batch sizes than other self-supervised learning models.

Documentation: https://docs.lightly.ai/examples/dcl.html
Decoupled Contrastive Learning paper: https://arxiv.org/abs/2110.06848

Model heads with default parameters
All model heads have now default parameters following the values of the original papers.

Create custom metadata config
Custom metadata in the Lightly Platform can now easily be configured via `ApiWorkflowClient.create_custom_metadata_config()`

Progress bar for video dataset initialization
Constructing a `LightlyDataset` with large video datasets can take long, as all frames in all videos have to be counted. We added a tqdm progress bar for it.

Models
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction, 2021](https://arxiv.org/abs/2103.03230)
- [Bootstrap your own latent: A new approach to self-supervised Learning, 2020](https://arxiv.org/abs/2006.07733)
- [DCL: Decoupled Contrastive Learning, 2021](https://arxiv.org/abs/2110.06848)
- [DINO: Emerging Properties in Self-Supervised Vision Transformers, 2021](https://arxiv.org/abs/2104.14294)
- [MoCo: Momentum Contrast for Unsupervised Visual Representation Learning, 2019](https://arxiv.org/abs/1911.05722)
- [NNCLR: Nearest-Neighbor Contrastive Learning of Visual Representations, 2021](https://arxiv.org/pdf/2104.14548.pdf)
- [SimCLR: A Simple Framework for Contrastive Learning of Visual Representations, 2020](https://arxiv.org/abs/2002.05709)
- [SimSiam: Exploring Simple Siamese Representation Learning, 2020](https://arxiv.org/abs/2011.10566)
- [SwAV: Unsupervised Learning of Visual Features by Contrasting Cluster Assignments, M. Caron, 2020](https://arxiv.org/abs/2006.09882)

More stable image download
Lightly now also retries an image download if the read url exists at first, but becomes unavailable during the download.

More stable video frame download
Some videos drop frames if seeking to keyframes is used. Lightly now detects this case and handles it by retrying the reading without seeking.

Models
- [Bootstrap your own latent: A new approach to self-supervised Learning, 2020](https://arxiv.org/abs/2006.07733)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction, 2021](https://arxiv.org/abs/2103.03230)
- [DINO: Emerging Properties in Self-Supervised Vision Transformers, 2021](https://arxiv.org/abs/2104.14294)
- [SimSiam: Exploring Simple Siamese Representation Learning, 2020](https://arxiv.org/abs/2011.10566)
- [MoCo: Momentum Contrast for Unsupervised Visual Representation Learning, 2019](https://arxiv.org/abs/1911.05722)
- [SimCLR: A Simple Framework for Contrastive Learning of Visual Representations, 2020](https://arxiv.org/abs/2002.05709)
- [NNCLR: Nearest-Neighbor Contrastive Learning of Visual Representations, 2021](https://arxiv.org/pdf/2104.14548.pdf)
- [SwAV: Unsupervised Learning of Visual Features by Contrasting Cluster Assignments, M. Caron, 2020](https://arxiv.org/abs/2006.09882)