You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I understand the purpose, but I don't understand how it works. Logits can be big negative numbers. How can you improve the numerical stability of the softmax() operation by adding a small positive number to logits?
On the other hand, adding a small positive number to softmax makes the log() operation more robust.
It should be
epsilon = tf.constant(value=1e-4)
softmax = tf.nn.softmax(logits) + epsilon
The text was updated successfully, but these errors were encountered: