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

explanation in 3_alexnet #17

Open

yf291115925 opened this issue Aug 1, 2022 · 0 comments

yf291115925 commented Aug 1, 2022

The images in the CIFAR10 dataset are significantly more complex than the MNIST dataset. They are larger, have three times the amount of pixels and are more cluttered. This makes them harder to learn and consequently means we should use less augmentation.

less --> more?

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