Skip to content

Instantly share code, notes, and snippets.

@ShakeDewan

ShakeDewan/keras_logistic_regression.py

Forked from fchollet/keras_logistic_regression.py
Created July 4, 2019 16:02
Show Gist options
  • Save ShakeDewan/7608edc4bd1df66b1ce29a30894a40a5 to your computer and use it in GitHub Desktop.
Save ShakeDewan/7608edc4bd1df66b1ce29a30894a40a5 to your computer and use it in GitHub Desktop.
Download ZIP

Revisions

  1. @fchollet fchollet created this gist Aug 13, 2016.
    27 changes: 27 additions & 0 deletions keras_logistic_regression.py
    View file
    Original file line number Diff line number Diff line change
    @@ -0,0 +1,27 @@
    from keras.models import Sequential
    from keras.layers import Dense

    x, y = ...
    x_val, y_val = ...

    # 1-dimensional MSE linear regression in Keras
    model = Sequential()
    model.add(Dense(1, input_dim=x.shape[1]))
    model.compile(optimizer='rmsprop', loss='mse')
    model.fit(x, y, nb_epoch=10, validation_data=(x_val, y_val))

    # 2-class logistic regression in Keras
    model = Sequential()
    model.add(Dense(1, activation='sigmoid', input_dim=x.shape[1]))
    model.compile(optimizer='rmsprop', loss='binary_crossentropy')
    model.fit(x, y, nb_epoch=10, validation_data=(x_val, y_val))

    # logistic regression with L1 and L2 regularization
    from keras.regularizers import l1l2

    reg = l1l2(l1=0.01, l2=0.01)

    model = Sequential()
    model.add(Dense(1, activation='sigmoid', W_regularizer=reg, input_dim=x.shape[1]))
    model.compile(optimizer='rmsprop', loss='binary_crossentropy')
    model.fit(x, y, nb_epoch=10, validation_data=(x_val, y_val))