If, as a by-product of the forward pass of the layer, you end up with any loss or metric you want to track during training, just use `self.add_loss` or `self.add_metric`.pic.twitter.com/QBMSIm2hQV
Show this thread
A quick tweetorial. This is how you create a new Keras layer. You can either create the weights upon layer instantiation, in `__init__()`, or create them lazily in `build()` based on the first input shape seen.pic.twitter.com/6iBPpcpAAA
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Would be great if u can hashtag your nice “tweetorial”
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
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.