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.

Sign up for GitHub

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

Jump to bottom

[VISION] Improve image augmentation for object detection #91

Open
1 of 4 tasks
dgarlor opened this issue Nov 10, 2022 · 0 comments
Open
1 of 4 tasks

[VISION] Improve image augmentation for object detection #91

dgarlor opened this issue Nov 10, 2022 · 0 comments
Labels
3 - Quality of Life Not a priority enhancement New feature or request VISION Issue related to the VISION template

Comments

@dgarlor
Copy link
Contributor

dgarlor commented Nov 10, 2022 •
edited by gsolard
Loading

Problem

Data augmentation can improve the results of the object detection algorithms. Current augmentation includes only basic rotations and flips.

Concerned template

  • NLP template
  • NUM template
  • VISION template
  • How templates are generated - Jinja

Solution

I have used ImgAug in some vision projects and it's very useful. It will modify the coordinates of the boxes when applying transforms!
@dgarlor dgarlor added the enhancement New feature or request label Nov 10, 2022
@gsolard gsolard added VISION Issue related to the VISION template 3 - Quality of Life Not a priority labels Nov 10, 2022
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
3 - Quality of Life Not a priority enhancement New feature or request VISION Issue related to the VISION template
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@dgarlor @gsolard