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

Updates to SustainBenchCropYield dataset #1756

Merged
merged 3 commits into from
Dec 7, 2023
Merged

Conversation

calebrob6
Copy link
Member

@calebrob6 calebrob6 commented Dec 4, 2023

Fixes #1754 -- the whole dataset is only 291Mb so we can safely load all of this in the constructor then just access it in __getitem__ (this also only takes a few seconds at most).

This PR also updates the dataset to download the "soybeans_updated.zip" file from https://drive.google.com/drive/folders/1hsp2PlXAgcQ0pbx_vvPKHZcj_Am3rWx4 which appears to be the version of the dataset that the benchmark results reported here https://sustainlab-group.github.io/sustainbench/leaderboard/#crop-yield-prediction are based off of.

@chrisyeh96 in case you are interested!

@github-actions github-actions bot added the datasets Geospatial or benchmark datasets label Dec 4, 2023
@adamjstewart adamjstewart added this to the 0.5.2 milestone Dec 7, 2023
@adamjstewart adamjstewart merged commit 9577ac7 into main Dec 7, 2023
21 checks passed
@adamjstewart adamjstewart deleted the sustainbench_fix branch December 7, 2023 15:27
isaaccorley pushed a commit that referenced this pull request Mar 2, 2024
* Updating download, fixing __getitem__ speed

* Formatting

* Update torchgeo/datasets/sustainbench_crop_yield.py
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
datasets Geospatial or benchmark datasets
Projects
None yet
Development

Successfully merging this pull request may close these issues.

SustainBenchCropYield reads all the data on __getitem__
3 participants