I'm training a very complex function in tensorflow. Is there a way to decrease the learning rate only when the cost isin't decreasing very much?
$\begingroup$
$\endgroup$
-
$\begingroup$ Just keep track of the objective function and use a conditional to set the leraning rate if it drops. $\endgroup$ – Emre Nov 11 '17 at 18:40
-
$\begingroup$ I couldn't do it in tensorflow, is there any example of how something like this is done in tensorflow? $\endgroup$ – Rishi Swethan Nov 11 '17 at 18:48
-
$\begingroup$ tensorflow.org/api_docs/python/tf/cond and tensorflow.org/api_docs/python/tf/train/… $\endgroup$ – Emre Nov 11 '17 at 19:13
