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

image transformations for improved encoding #829

Closed
4 of 5 tasks
jeff-regier opened this issue Jun 23, 2023 · 0 comments · Fixed by #878
Closed
4 of 5 tasks

image transformations for improved encoding #829

jeff-regier opened this issue Jun 23, 2023 · 0 comments · Fixed by #878
Assignees
Milestone

Comments

@jeff-regier
Copy link
Contributor

jeff-regier commented Jun 23, 2023

Evaluate whether/which transformations of images improve encoder performance. Some transformations to consider:

  • log (with various offsets and rescalings)
  • sigmoid (with various offsets and rescalings)
  • stacking/coaddition (across bands)
  • z-scoring (per pixel, at perhaps other ways too)
  • compositions of the above transformations

For all these, Hydra multi-run should be helpful. We'd like to keep a record or what did/didn't work well.

@jeff-regier jeff-regier added this to the version 0.3 milestone Jul 4, 2023
@jeff-regier jeff-regier linked a pull request Jul 20, 2023 that will close this issue
sawanp813 added a commit that referenced this issue Aug 4, 2023
* rolling z-score model standard + unalign-realign case study

* removing unnecessary transforms

---------

Co-authored-by: Sawan Patel <sawanpa@deeplearning-01.stat.lsa.umich.edu>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging a pull request may close this issue.

2 participants