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

2.4 Transfer Learning & Fine-Tuning.ipynb #2

Open

michael135 opened this issue Jul 25, 2017 · 0 comments

michael135 commented Jul 25, 2017 •

edited

Loading

After "re-training" I checked again the preformance on X_train_lt5 and X_test_lt5 and it's accuracy decreased from ~99% to ~40%.

I believe in retraining the "old examples" should be partially combined with a new ones...

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