lightly-ai / lightly-ai/lightly

Read Multispectral data for Remote Sensing using LightlyDataset

Open
#1,780 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
3.8k
Forks
367
Avg merge
3d 22h
Merged PRs (30d)
5

Description

Not so much as an issue, but I am trying to use Self-Supervised Learning on a remote sensing dataset and wondering if there is a way to read Multispectral data which has beyond the 3 RGB Bands. The data I have compiled is from Sentinel2A and has 13 bands, so I believe that LightlyDataset cannot read these as they are loaded through PIL from what I understand.

Any idea how I can extend the LightlyDataset to more than the 3 RGB bands ?. Also if this is possible will it still cause issues with other functions such as transformations (e.g DinoTransforms) ?.
I am speculating here, but will things like color jitter or rotations be applicable in such cases.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reviewing the LightlyDataset and DinoTransforms entry points mentioned in the issue, along with how PIL-loaded inputs are handled. Determine whether 13-band Sentinel2A data can be supported and which transformations remain valid; done means the supported input behavior and transformation limitations are clearly established.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision, machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.