Group Abstract Group Abstract

Message Boards Message Boards

0
|
576 Views
|
2 Replies
|
1 Total Like
View groups...
Share
Share this post:

Documentation says we can provide a loss layer to NetTrain as 3rd argument, why doesn't this work?

Iuval Clejan
Posted 1 month ago

I tried with and without explicit loss layer. Neither works.
POSTED BY: Iuval Clejan
2 Replies
Sort By:
Iuval Clejan
Iuval Clejan
Posted 1 month ago

Giulio, you are my hero! Can you please tell me how to extract the parameters for my user-defined "quadratic" layer? I know how to extract weights from a linear layer, but I am not understanding the syntax in general. See file enclosed.
POSTED BY: Iuval Clejan

Hi Iuval,

the third argument is used to extract training properties. To specify the probability cross-entropy instead of the index based one, you must use the LossFunction option.

Try this:

famTrained = NetTrain[famNet, trainingdatafam,
   LossFunction -> CrossEntropyLossLayer["Probabilities"]]
POSTED BY: Giulio Alessandrini
Reply to this discussion
Community posts can be styled and formatted using the Markdown syntax.
Tag limit exceeded
Note: Only the first five people you tag will receive an email notification; the other tagged names will appear as links to their profiles.
Reply Preview
Attachments
Remove
or Discard