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

Can this project deal with datasets with over 2 classes? #5

Open
zetn opened this issue Sep 28, 2017 · 4 comments
Open

Can this project deal with datasets with over 2 classes? #5

zetn opened this issue Sep 28, 2017 · 4 comments

Comments

@zetn
Copy link

zetn commented Sep 28, 2017

Hello, I wanna ask about if this project can dealt with datasets with over 2 classes, Like cifar10?

@duggalrahul
Copy link
Owner

Yes.
Just set the nb_classes variable to the number of classes you want. I'm not sure if AlexNet can accept inputs as small as in the CIFAR 10 dataset. You can possibly remove some pooling layers to accommodate small sized image.

Best,
Rahul

@G33kyKitty
Copy link

Hello, why did you use nb_classes to be 2??

@Gokkulnath
Copy link

@G33kyKitty Because he has used Pre-trained weights for Binary Classification. (Cat/Dog)

@G33kyKitty
Copy link

Ok thank you @Gokkulnath ..

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

No branches or pull requests

4 participants