-
Notifications
You must be signed in to change notification settings - Fork 47
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
Datasets #7
Comments
Hi, The number counts flipped images as well. There are 22K images (11K pairs) in total, however, you can generate more given the code in github. |
Thanks!
Thanks! |
Hi, |
Just like this:
|
Hi, To generate synthetic dataset, you should download images from COCO first. If you have COCO images already, then the path might be wrong. |
Hi, |
hi,i am a postgraduate who focused on image forgery detection, I'm reproducing this network, too. can you add my wechat so we can talk to each other. My wechat: L691017063 |
Maybe you can try this in demo.py: |
Hi,
Is there only 11,835 images in the dataset download link provided? I remember that the paper said that there is a 42K tampered and authentic image pairs.
The text was updated successfully, but these errors were encountered: