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

NaN Loss Forecasting Model #1

Open

JINHXu opened this issue Feb 26, 2023 · 2 comments

Owner

JINHXu commented Feb 26, 2023

https://stackoverflow.com/questions/37232782/nan-loss-when-training-regression-network

Owner Author

JINHXu commented Feb 26, 2023

NaN loss due to new features, fixes:

data
- feature values 0.0 -> 1.0
- dropna
model params
- lower learning rate
- increase batch size
- optimizer clipnorm=1
- add l1/l2 penalty
- reduce number of neurons in the input layer
- reduce network size

Owner Author

JINHXu commented Feb 26, 2023

keras-team/keras#2134

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