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

Output of the CNN network #1

Open

giusarno opened this issue Jun 27, 2021 · 1 comment

giusarno commented Jun 27, 2021

Hello,
thanks for the code. I have 2 questions about the output of the CNN network.

Why is the output of the network a vector of 2 ? I have seen other Siamese network have a different output but never correlated to job the net has to do.
How would I then use the network for inference ?

Owner

seanbenhur commented Jun 29, 2021 •

edited

Loading

Hi,

The output of the model is the vector of two, due to contrastive loss, which is a similarity based distance metric
Right now, you can use this code starting from this line which predicts for all the images in the test dataset, If I have time I will rewrite it function for single set of signatures

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