Beste way to process big datasets


Hello everyone!

I want to process big datasets, like 5000+ images. Since this amount of data is probably going to need a lot of resources and time, I would like to know how to process these amounts of data the most efficient way.

I was thinking about using this command

docker run -ti --rm -v $(pwd):/datasets/code opendronemap/opendronemap --project-path /datasets --time --verbose --min-num-features 2000

Is there a way in ODM to split the dataset into smaller subsets and process these first and at last kind of combine all subresults to a big result?

Any advices would be appreciated!


Check out the split-merge approach. It’s not fully mature, but should help a lot with large datasets: