Matt Watson
Matt Watson
It is expected that when passing a custom callable to either the `standardize` or `split` arguments of `TextVectorization`, that the function will need to be registered with `register_keras_serializable` or passed...
Hi! Thanks for filing, sorry for the delay here. Do you have an idea of how much horizontal scaling you would need? What's your use case/data size? We talked about...
This is a known bug with some special classes we introduced for handling StaticHashTable and MutableHashTable in keras layers (TrackableWeightHandler and VocabWeightHandler). Both the classes have caused a number of...
This bug appears to be fixed on 2.9 actually! You can check that by changing your loading line to ``` new_model = keras.models.load_model('/content/my_awaesome_model', custom_objects={"Model": Model}) ``` Hits the error you...
Checked with people today, we should not need the custom objects for subclass model to work. So I think this bug can be marked fixed, but we will need to...
@aflah02 here is the sentencepiece one!
Assigning myself as a placeholder; this will need to be done by someone on the keras team.
For sure we want symbol documentation and guides on keras.io, and possibly in the future on tensorflow.org as well. So we will use the tooling for documentation generation for [keras-io](https://github.com/keras-team/keras-io),...
Sure thing! Though for small issues like these, try to leave some of these available for newcomers to the project as well. Thanks!
Thank you! Please tag me for review!