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

Image inpainting using vgg19 #10

Open
NerminSalem opened this issue Mar 28, 2017 · 4 comments
Open

Image inpainting using vgg19 #10

NerminSalem opened this issue Mar 28, 2017 · 4 comments

Comments

@NerminSalem
Copy link

is it possible to make the vgg19 model complete missing parts of an image according to its category ?
thanks
@NerminSalem
Copy link
Author

@leriomaggio
@ypeleg
can u help?

@leriomaggio
Copy link
Owner

I don't even get the question... I'm sorry!!
Could you please rephrase? Thanks

@NerminSalem
Copy link
Author

i m trying to re-implement the work of "IMAGE INPAINTING THROUGH NEURAL NETWORKS HALLUCINATIONS" so he extracted the features from the vgg19 (last layer) and inverted them to get the missing parts of the image
the work is really interesting but there are no details of how the authors did it so i m starting all from scratch
sorry if my question was clumsy :)

@ngragaei
Copy link

from kaggle_data import load_data, preprocess_data, preprocess_labels
I do not understand this step. Can you explain please.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@leriomaggio @ngragaei @NerminSalem