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

2C (dimensionality reduction) + 2FC network 93.6% test acc, 0.6M parameters #149

Open
dtoertei opened this issue Aug 27, 2019 · 0 comments

Comments

@dtoertei
Copy link

Successfully reached >93% test set accuracy with this convnet (Conv2Dsimple2) without data augmentation.
Used stratified 3-fold train, dropout, batch normalization and max norm.

Code and description is available here: https://github.com/dtoertei/fashion-mnist

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

1 participant