Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add BioMassters Dataset #1560

Merged
merged 18 commits into from
Sep 29, 2023
Merged

Conversation

nilsleh
Copy link
Collaborator

@nilsleh nilsleh commented Sep 12, 2023

This PR adds the BioMassters Dataset which was part of this Driven Data Challenge and currently under review as a paper. It consists of Sentinel 1 and 2 data as well as corresponding Aboveground Biomass pixelwise targets and is an effort lead by @nascetti-a . If you should have any comments or suggestions, feel welcome to do so.

TODOs:

  • waiting to download the full data on my side to finish the directory structure and tests
  • automatic download of dataset and verify
  • fix plotting of S1

Example Plots:
Screenshot from 2023-09-14 10-58-52
Screenshot from 2023-09-14 10-58-02

@nilsleh nilsleh marked this pull request as draft September 12, 2023 13:35
@github-actions github-actions bot added datasets Geospatial or benchmark datasets testing Continuous integration testing labels Sep 12, 2023
@nilsleh nilsleh marked this pull request as ready for review September 15, 2023 15:47
Copy link
Collaborator

@adamjstewart adamjstewart left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Need to add to docs

tests/data/biomassters/data.py Show resolved Hide resolved
tests/data/biomassters/data.py Outdated Show resolved Hide resolved
torchgeo/datasets/biomassters.py Outdated Show resolved Hide resolved
torchgeo/datasets/biomassters.py Outdated Show resolved Hide resolved
torchgeo/datasets/biomassters.py Outdated Show resolved Hide resolved
torchgeo/datasets/biomassters.py Show resolved Hide resolved
torchgeo/datasets/biomassters.py Outdated Show resolved Hide resolved
torchgeo/datasets/biomassters.py Show resolved Hide resolved
torchgeo/datasets/biomassters.py Outdated Show resolved Hide resolved
cross_polarization = img[1] # transmit != receive
ratio = co_polarization / cross_polarization

# https://gis.stackexchange.com/a/400780/123758
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This only works for certain scales, see: #1151 (comment)

If you can't get it working, you can always plot them as separate grayscale images like I did for SSL4EO-S12. Maybe @RitwikGupta can help if he has time

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I assume this is still broken? We could fix it in a follow-up patch release I suppose.

@adamjstewart adamjstewart added this to the 0.5.0 milestone Sep 25, 2023
@github-actions github-actions bot added the documentation Improvements or additions to documentation label Sep 28, 2023
tests/datasets/test_biomassters.py Outdated Show resolved Hide resolved
tests/datasets/test_biomassters.py Outdated Show resolved Hide resolved
torchgeo/datasets/biomassters.py Outdated Show resolved Hide resolved
torchgeo/datasets/biomassters.py Outdated Show resolved Hide resolved
torchgeo/datasets/biomassters.py Outdated Show resolved Hide resolved
torchgeo/datasets/biomassters.py Outdated Show resolved Hide resolved
torchgeo/datasets/biomassters.py Outdated Show resolved Hide resolved
torchgeo/datasets/biomassters.py Show resolved Hide resolved
torchgeo/datasets/biomassters.py Outdated Show resolved Hide resolved
torchgeo/datasets/biomassters.py Outdated Show resolved Hide resolved
@adamjstewart
Copy link
Collaborator

Updating the branch may fix the RtD tests

Copy link
Collaborator

@adamjstewart adamjstewart left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think the S1 plot is the only remaining thing that's broken. If we run out of time to fix this I'm fine with merging as is and fixing it in the future.

@adamjstewart adamjstewart merged commit 76f92f8 into microsoft:main Sep 29, 2023
20 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
datasets Geospatial or benchmark datasets documentation Improvements or additions to documentation testing Continuous integration testing
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants