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

Gap between theoric and output image size #55

Open
wants to merge 4 commits into
base: master
Choose a base branch
from

Conversation

jordangierschendorf
Copy link

@jordangierschendorf jordangierschendorf commented May 23, 2017

Multiple modifications.

  • Two new files for generate UNet model and predict new images.

  • My inputs are RGB images (.PNG) between [0;255] with dimension of 500x376. My masks are binary PNG images, [0;255] with only one component.

Be carreful, the issue is not still solved.

Jordan G added 4 commits May 17, 2017 17:59
ENH : change format of output images to tif. (because prediction is in float)
ADD : two new scripts for generate and predict model
ENH : save model and image from training in single directory.
@liuzhisheng1226
Copy link

Hello,
In my datasets,Image is 3 channels,Mask is Gray Scale Image,How to train it?
Thanks

@AziziShekoofeh
Copy link

Hi, any plan to merge this to the package any time soon :) ?! -Shekoofeh

@jakeret
Copy link
Owner

jakeret commented Jun 1, 2018

this PR is altering large portions of the code while modifying many different things at the same time. Therefore it's kinda hard for me to see how it affects the code base and how the code remains as generic as possible

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 this pull request may close these issues.

4 participants