Created by @RisingSayak and @soumikRakshit96 
Show this thread
New tutorial on http://keras.io : large-scale multi-label text classification -- predict the domain of an arXiv paper from its abstract. This tutorial features a brand new dataset collected from arXiv (also available on Kaggle).https://keras.io/examples/nlp/multi_label_classification/ …
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
It seems that you've been announcing one example per day lately. Great to see the involvement of the community! Those examples are pure gold. I've used several of them many times.
-
The Keras community has been doing an amazing job with these!
- Show replies
New conversation -
-
-
I wonder why repeat is not used in http://tf.data pipeline. Even I also kind of don’t use it but I do think it will provide a speedup when you run for multiple epochs!
-
Don't think so . Repeat kind of ensures that you will never run out of data. I always use repeat. Without that how will we train multiple epochs?
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.