I think it's great that both data scientists and DL researchers can now speak the same language, use the same APIs, at different levels of abstraction.
Show this thread
Subclassing tf.keras objects (Layer, Model, Metric...), together with eager execution & the GradientTape, bridges the gap from the lowest-level APIs to the highest-level features like Sequential and fit(). Full flexibility + productivity. Check it out: https://www.tensorflow.org/alpha/guide/keras/custom_layers_and_models …https://twitter.com/random_forests/status/1103428693660037121 …
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
This Tweet is unavailable.
-
With subclassing you have to separate state-building (in __init__ or build) and execution (in call). But if you use the functional API (where you can use custom layers too) you can do both in a single step.
End of conversation
-
-
-
Great! Congratulations!
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.