Improve Memory Efficiency for find_label_issues_batched method #853
Labels
enhancement
New feature or request
help-wanted
We need your help to add this, but it may be more challenging than a "good first issue"
Summary
This issue aims to track the enhancement proposal to improve memory efficiency for the
find_label_issues_batched
method.Problem
Users with large segmentation data have experienced memory issues due to the need for loading large datasets into memory with the current implementation of
find_label_issues_batched
.Suggested Solution
At a high level, a proposed solution is to make the method more memory-efficient by modifying it to iterate over images instead of points and ensuring that
flatten_and_preprocess
is called internally.Related Context
Issue #842 discusses the memory issues faced by a user when using the
find_label_issues
method on large datasets for segmentation.The text was updated successfully, but these errors were encountered: