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

Misc object detection fixes and improvements #1711

Merged
merged 11 commits into from Feb 20, 2023
Merged

Misc object detection fixes and improvements #1711

merged 11 commits into from Feb 20, 2023

Conversation

AdeelH
Copy link
Collaborator

@AdeelH AdeelH commented Feb 17, 2023

Overview

This PR makes multiple small fixes and improvements to object detection-related code. The most notable change is that it is now possible to use an img_sz that is not equal to the chip_sz during prediction.

Checklist

  • Added needs-backport label if PR is bug fix that applies to previous minor release
  • Ran scripts/format_code and committed any changes
  • Documentation updated if needed
  • PR has a name that won't get you publicly shamed for vagueness

Notes

N/A

Testing Instructions

See new unit tests.

@AdeelH AdeelH added the needs-backport This PR needs to be backported to release branches label Feb 20, 2023
@codecov
Copy link

codecov bot commented Feb 20, 2023

Codecov Report

Merging #1711 (f4f1ca4) into master (186e4f6) will increase coverage by 0.07%.
The diff coverage is 92.68%.

@@            Coverage Diff             @@
##           master    #1711      +/-   ##
==========================================
+ Coverage   75.62%   75.69%   +0.07%     
==========================================
  Files         192      192              
  Lines        9277     9304      +27     
==========================================
+ Hits         7016     7043      +27     
  Misses       2261     2261              
Impacted Files Coverage Δ
...ision/core/evaluation/classification_evaluation.py 90.69% <ø> (ø)
...sion/core/evaluation/object_detection_evaluator.py 75.00% <ø> (+8.33%) ⬆️
...vision/pytorch_backend/pytorch_object_detection.py 42.10% <ø> (ø)
...data/label_store/object_detection_geojson_store.py 62.96% <66.66%> (+0.46%) ⬆️
...rvision/core/data/label/object_detection_labels.py 93.91% <80.00%> (-0.57%) ⬇️
...vision/pytorch_learner/object_detection_learner.py 92.20% <92.85%> (+1.43%) ⬆️
...data/label_source/object_detection_label_source.py 55.22% <100.00%> (+0.67%) ⬆️
...n_core/rastervision/core/data/label_store/utils.py 82.60% <100.00%> (+4.83%) ⬆️
...ytorch_learner/dataset/object_detection_dataset.py 46.55% <100.00%> (+0.46%) ⬆️
...ervision/pytorch_learner/object_detection_utils.py 76.79% <100.00%> (+1.65%) ⬆️
... and 1 more

Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here.

@AdeelH AdeelH marked this pull request as ready for review February 20, 2023 12:38
@AdeelH AdeelH merged commit f022ff1 into azavea:master Feb 20, 2023
@AdeelH AdeelH deleted the od branch February 20, 2023 12:39
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
needs-backport This PR needs to be backported to release branches
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

1 participant