lightly-ai / lightly-ai/lightly
Read Multispectral data for Remote Sensing using LightlyDataset
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
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- 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