CODEWITHSUNDEEP
pythonkerasregressionlinear-regressionclip
PascalVKooten
PascalVKooten

Reputation: 21453

How can I clip the values returned by a layer in Keras?

How can I clip the values returned by the Lambda layer?

I tried using this:

from keras.backend.tensorflow_backend import clip
from keras.layers.core import Lambda

...
model.add(Dense(1))
model.add(Activation('linear'))
model.add(Lambda(lambda x: clip(x, min_value=200, max_value=1000)))

But it does not matter where I put my Lambda+clip, it does not affect anything?

Upvotes: 7

Views: 7728

Answers (2)

Andrew Hryvachevskyi
Andrew Hryvachevskyi

Reputation: 115

Try this solution:

tf.clip_by_value(yur_values, clip_value_min=0, clip_value_max=1)

Upvotes: 2

PascalVKooten
PascalVKooten

Reputation: 21453

It actually has to be implemented as loss, at the model.compile step. 

from keras import backend as K

def clipped_mse(y_true, y_pred):
    return K.mean(K.square(K.clip(y_pred, 0., 1900.) - K.clip(y_true, 0., 1900.)), axis=-1)

model.compile(loss=clipped_mse)

EDIT: Actually, now in hindsight I think that this might not be the right approach. This actually means we do not add penalty for going over too high of a values - it's in a way the opposite of what we want.

Upvotes: 5

Related Questions