Can someone inform me why we need tf.clip_by_value(x,-1,1) before tf.sign(x)

[Sibo-tao]

I do not understand why there are two lines of codes in binarize(x): x=tf.clip_by_value(x,-1,1) return tf.sign(x)

because clipping will not change the sign of x. Why we need the first line?

[jonkoi]

I think it is the way to reinforce straight through estimator because tf.clip_by_value happens to zero out out gradients for x out of bound.

[12baby21]

I have the same question. The tf.clip_by_value seems to be redundant before tf.sign.