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

Hi there can i ask a question? #7

Closed
munkh-erdene opened this issue Dec 5, 2018 · 4 comments
Closed

Hi there can i ask a question? #7

munkh-erdene opened this issue Dec 5, 2018 · 4 comments

Comments

@munkh-erdene
Copy link

First of all thank you for sharing your code. Im just looking for this type code (predict future price). Now im testing but i got wrong predicted values. All predicted values are increased. Why?

@kladskull
Copy link

He has no idea.

@khasheloole
Copy link

because he does not use Dropout function in keras.layers
from keras.layers import Dropout
after each layer LTSM (layer) use:
model.add(Dropout(0.2))

adjust the value with your results

@nubonics
Copy link

First of all thank you for sharing your code. Im just looking for this type code (predict future price). Now im testing but i got wrong predicted values. All predicted values are increased. Why?

How did you predict more than one value at a time if you dont mind me asking?

@NourozR
Copy link
Owner

NourozR commented May 9, 2021

This was a very intro level code. If you keep changing dataset, it wouldn't work in the same way. Secondly, a lot of things has changed now in Keras and deep learning but basic things are still the same. Please check the recent documentation but like someone advised to use Dropout layers - please try that.

Finally, someone said - "he has no idea" - to him, I would like to say - "Hey, I do". You can come and learn from me anytime. Thanks!

@NourozR NourozR closed this as completed May 9, 2021
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

5 participants