Naïve question: Is it then possible to retrain the model in such a way that all weights that have been set to the same value keep that same value (but that value might be tweaked)?
New in TensorFlow: weight clustering for Keras model optimization (contributed by @ARM). Smaller weights files via a more efficient encoding!
https://blog.tensorflow.org/2020/08/tensorflow-model-optimization-toolkit-weight-clustering-api.html …https://twitter.com/TensorFlow/status/1293219582010785795 …
Weight clustering is now part of the TensorFlow Model Optimization Toolkit! Many thanks to -
-
-
(Just read the linked paper, and at least in the case of the paper the answer seems to be yes)pic.twitter.com/k5StvZdWHd
End of conversation
New 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.