Skip to content

This fixes handling of cropped image size in the multi input model. #2

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
Open
samimideksa wants to merge 10 commits into
base: master
Choose a base branch
from
Open

This fixes handling of cropped image size in the multi input model. #2

samimideksa wants to merge 10 commits into from

Conversation

@samimideksa
Copy link

@samimideksa samimideksa commented Jun 5, 2018 •
edited
Loading

  • accept variable image size
  • read default arguments from config.json
  • reduced rotation range to 10 and deleted shear range from datagenerator to alleivatte underfitting problem
  • trained the model using lfw dataset for facial images containing 13000 facial images and helen dataset containing 2300 images with the original dataset
  • used adamax optimzer based on infinity norm to enhance the performance of the model. It's paper can be found in this link.

These changes can be merged with the original repository after a discussion with my colleague @mitiku1 .

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@ymitiku ymitiku ymitiku approved these changes

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@samimideksa @ymitiku