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

Compare performance of trained model with/without brightness augmentation #7

Open
mattmotoki opened this issue Oct 24, 2018 · 0 comments
Open

Compare performance of trained model with/without brightness augmentation #7

mattmotoki opened this issue Oct 24, 2018 · 0 comments
Labels
enhancement New feature or request

Comments

@mattmotoki
Copy link
Contributor

Brightness augmentation helps the model learn to predict images taken at different times of the day (low brightness corresponds to mornings/evenings/cloudy conditions, high brightness corresponds to midday).

  • To quantify improvement from brightness augmentation, train a model with/without augmentation
  • For each model, evaluate performance on a test set.
  • Plot test set performance vs degree of brightness transformation
@mrbarbasa mrbarbasa added the to do label Nov 1, 2018
@mrbarbasa mrbarbasa added enhancement New feature or request and removed to do labels Nov 8, 2018
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
enhancement New feature or request
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@mrbarbasa @mattmotoki