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

Alexnet high accuracy #6

Open

dzwallkilled opened this issue Sep 4, 2019 · 0 comments

dzwallkilled commented Sep 4, 2019

I trained the "Alexnet" in another implementation and got very high accuracy, around 85%.

The main differences between the two implementations are,

random cropping in train_transform "transforms.RandomCrop(32, padding=4)",
SGD optimizer with step-wise learning rate [100 150 180] (total 200 epochs) and an initial learning rate 0.1.

Is this high accuracy possible?

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