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

Update crop type mapping workflow #85

Merged
merged 9 commits into from
Jun 27, 2024
Merged

Update crop type mapping workflow #85

merged 9 commits into from
Jun 27, 2024

Conversation

kvantricht
Copy link
Contributor

This workflow is still the modular one with separated UDFs for feature extraction and model inference as for the moment there is no indication that merging them speeds things up. Ultimately we still may want to do the merging to have a cleaner process graph that is easier to debug and optimize.

This PR includes automated cropland masking for the crop type products, including @jdries verified temporary fix of reduce_dimension on the cropland mask. By running generate_map with product_type="croptype", the crop type workflow can be triggered.

Example usage (both for cropland and croptype) can be found in scripts/inference/cropland_mapping.py.

Currently specifying a custom model URL is not supported yet. Need to discuss with @GriffinBabe on an elegant way to parse parameters.

src/worldcereal/job.py Outdated Show resolved Hide resolved
src/worldcereal/job.py Show resolved Hide resolved
Copy link
Contributor

@jdegerickx jdegerickx left a comment

Choose a reason for hiding this comment

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

Only one comment from my side but it's not a breaking issue at the moment so we can proceed

@kvantricht kvantricht merged commit 595099c into main Jun 27, 2024
1 check passed
@kvantricht kvantricht deleted the cropland-masking branch June 27, 2024 13:55
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants