Skip to content

Instantly share code, notes, and snippets.

Embed
What would you like to do?
Implementing linear regression in keras
"""
Author: Shubhanshu Mishra
Posted this on the keras issue tracker at: https://github.com/fchollet/keras/issues/108
Implementing a linear regression using Keras.
"""
from keras.models import Sequential
from keras.layers.core import Dense, Activation
model = Sequential()
model.add(Dense(2,1,init='uniform', activation='linear'))
model.compile(loss='mse', optimizer='rmsprop')
model.fit(X_train, y_train, nb_epoch=1000, batch_size=16,verbose=0)
model.fit(X_train, y_train, nb_epoch=1, batch_size=16,verbose=1)
score = model.evaluate(X_test, y_test, batch_size=16)
@scottlawsonbc

This comment has been minimized.

Copy link

@scottlawsonbc scottlawsonbc commented Jun 17, 2016

No longer works on the latest version of Keras

@riders994

This comment has been minimized.

Copy link

@riders994 riders994 commented Jun 12, 2017

@scottlawsonbc This will work if you reformat the Dense layer to the new format.

@qks1lver

This comment has been minimized.

Copy link

@qks1lver qks1lver commented Jul 12, 2017

Hello, I'm knew to Keras. Can you show me how to write it with the new Dense format? Thanks!

@peachthiefmedia

This comment has been minimized.

Copy link

@peachthiefmedia peachthiefmedia commented Aug 7, 2017

@qks1lver it should be model.add(Dense(1, input_dim=2)) for the new api I think assuming 1 output from two input

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
You can’t perform that action at this time.