New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Multi label classification conversion #18772
base: master
Are you sure you want to change the base?
Multi label classification conversion #18772
Conversation
Thanks for the PR!
|
@fchollet : the code runs well on all 3 backends, in particular for fitting a Keras model, up to the section where the text preprocessing (TextVectorization layer) is included within a Keras.model (line 388). This part only works with TensorFlow. I understand that this is expected since TextVectorization layer uses TensorFlow internally and it is recommended that it be used outside of the model itself. |
Title: Large-scale multi-label text classification | ||
Author: [Sayak Paul](https://twitter.com/RisingSayak), [Soumik Rakshit](https://github.com/soumik12345) | ||
Date created: 2020/09/25 | ||
Last modified: 2023/11/13 (conversion to Keras 3 by @ben-ad) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Add a line "Converted to Keras 3 by:" at the end instead
asynchronous data processing. | ||
""" | ||
|
||
# Create a model for inference. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Since this won't work for other backends, better to show an example where we map the text_vectorizer into the tf.data Dataset. We need the code to run with all backends.
This PR is stale because it has been open for 14 days with no activity. It will be closed if no further activity occurs. Thank you. |
This PR is stale because it has been open for 14 days with no activity. It will be closed if no further activity occurs. Thank you. |
Hi @ben-ad Any update on this PR? Please. Thank you! |
Hi @ben-ad Any update on this PR? Please. Thank you! |
Git Diff can be seen here: ben-ad@2cc0190