Quick question about setting parameters
mk
New Altair Community Member
Hello,
I have a simple question which i cant seem to be able to figure out. I have two neural nets on different levels in my process hierarchy. Is it possible to somehow copy the parameters of one (which are set by a parent optimize parameters process) to the other? I have tried passing them using the "clone parameters" process but without success (one problem is that the NN has no input in which i could plug in the clone parameters, also a number of inputs which i would need to make a path from one NN to the other are simply not there). Basically i want both NNs to use the same parameters and i cant figure out how to achieve that.
Thanks in advance for any help.
I have a simple question which i cant seem to be able to figure out. I have two neural nets on different levels in my process hierarchy. Is it possible to somehow copy the parameters of one (which are set by a parent optimize parameters process) to the other? I have tried passing them using the "clone parameters" process but without success (one problem is that the NN has no input in which i could plug in the clone parameters, also a number of inputs which i would need to make a path from one NN to the other are simply not there). Basically i want both NNs to use the same parameters and i cant figure out how to achieve that.
Thanks in advance for any help.
Tagged:
0
Answers
-
Hi,
just add the Clone Parameters operator before the second NN, but after the optimization and enter the name of the NN operator in the optimization as "source" in the name map of the clone operator and the second NN as target.
Hope this helps,
Cheers, Marius0 -
I managed to get it working in the meantime using set parameters. Thanks for the explanation.0