@DynamicWebPaige I am testing the daily build of @TensorFlow 2.0 and it looks like tf.train.RMSPropOptimizer was removed. What is the best path to figure out where it went or why it was removed.
-
-
Heck Yes, I'll try it out!
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
What is the best way to apply clipping in 2.0? I checked the 2.0 documentation, and the optimizers do not have a parameter to set clip value to. What I am thinking is get the gradient, use the tf.keras.backend.clip(), then set the gradient values and backpropogate
-
Or does the tf.keras.optimizers implement the api functionality similar to keras, where clipnorm or clipvalue arguments can be used for all optimizers: https://keras.io/optimizers/
@martin_wicke - Show replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
2.0 docs: