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

feat: Added box coord clipping and target validation for detection tasks #355

Merged
merged 3 commits into from
Jul 6, 2021

Conversation

fg-mindee
Copy link
Contributor

This PR introduces the following modifications:

  • added box coord clipping to avoid rounding errors in detection datasets
  • added target validation for detection models to avoid silent failures
  • added unittests for target validation

Any feedback is welcome!

@fg-mindee fg-mindee added type: enhancement Improvement module: models Related to doctr.models module: datasets Related to doctr.datasets labels Jul 6, 2021
@fg-mindee fg-mindee added this to the 0.3.1 milestone Jul 6, 2021
@fg-mindee fg-mindee self-assigned this Jul 6, 2021
@codecov
Copy link

codecov bot commented Jul 6, 2021

Codecov Report

Merging #355 (d9ab964) into main (9f7edcd) will increase coverage by 0.00%.
The diff coverage is 100.00%.

Impacted file tree graph

@@           Coverage Diff           @@
##             main     #355   +/-   ##
=======================================
  Coverage   96.09%   96.10%           
=======================================
  Files          83       83           
  Lines        3404     3412    +8     
=======================================
+ Hits         3271     3279    +8     
  Misses        133      133           
Flag Coverage Δ
unittests 96.10% <100.00%> (+<0.01%) ⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files Coverage Δ
doctr/datasets/detection.py 96.87% <100.00%> (ø)
...dels/detection/differentiable_binarization/base.py 91.92% <100.00%> (+0.20%) ⬆️
doctr/models/detection/linknet/base.py 88.31% <100.00%> (+0.64%) ⬆️

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update 9f7edcd...d9ab964. Read the comment docs.

Copy link
Collaborator

@charlesmindee charlesmindee left a comment

Choose a reason for hiding this comment

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

Thanks!

@fg-mindee fg-mindee merged commit 26e6971 into main Jul 6, 2021
@fg-mindee fg-mindee deleted the det-model branch July 6, 2021 12:36
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
module: datasets Related to doctr.datasets module: models Related to doctr.models type: enhancement Improvement
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants