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

Fine Tuning VGG16 for CIFAR10 #79

Open
Tracked by #77
mehulrastogi opened this issue Aug 31, 2021 · 3 comments
Open
Tracked by #77

Fine Tuning VGG16 for CIFAR10 #79

mehulrastogi opened this issue Aug 31, 2021 · 3 comments
Labels
easy An easy issue good first issue Good for newcomers Priority:Low Low Priority Tutorials Used for Tutorials

Comments

@mehulrastogi
Copy link
Contributor

mehulrastogi commented Aug 31, 2021

Training (or getting a pre trained model) the VGG16 network for One Pixel Attack Tutorial. This can also be used by other attacks.

@mehulrastogi mehulrastogi changed the title Fine Tuning VGG16 for CIFAR10 (refer table 4) Fine Tuning VGG16 for CIFAR10 Aug 31, 2021
@mehulrastogi mehulrastogi added good first issue Good for newcomers Priority:Low Low Priority Tutorials Used for Tutorials easy An easy issue labels Aug 31, 2021
@mehulrastogi
Copy link
Contributor Author

@Adversarial-Deep-Learning/computer-vision We can possibly store this on drive if someone does try retraining this. (or it is highly likely that someone can find a direct link to this on github somewhere )

@Shreyas-Bhat
Copy link
Contributor

Hey, I would like to work on this

@pronoma
Copy link
Contributor

pronoma commented Sep 12, 2021

https://github.com/geifmany/cifar-vgg
I found this existing implementation of VGG16 for CIFAR-10, but they've used Keras instead of PyTorch. Will this work? Otherwise I would like to take it up...

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
easy An easy issue good first issue Good for newcomers Priority:Low Low Priority Tutorials Used for Tutorials
Projects
None yet
Development

No branches or pull requests

3 participants