Great API, I used this quite a few times recently! Btw, I think in this setting you can just call `super()` without any arguments in the `__init__()`, right?
Tweetorial: this is how you create a custom metric in Keras. 1. Create state variables in `__init__()` 2. Update them in `update_state()` 3. Return metric value in `result()` 4. Reset state variables in `reset_states()` You can then use it just the same as built-in metrics.pic.twitter.com/NGZCt08KcH
-
-
-
Yes, no need to pass those arguments to super(): https://docs.python.org/3/library/functions.html#super …
End of conversation
New conversation -
-
-
What if a custom metric needs to return several distinct results? For instance, mean Average Precision. Is it possible to compute the usual AP, AP@50, AP@75, AR all at onece?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
This Tweet is unavailable.
-
They've been part of the API for years.https://keras.io/api/metrics/
End of 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.