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.
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.
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