@XGBoostProject is also very popular
People say TensorFlow completely dominates the machine learning ecosystem, but that's not entirely true. Scikit-Learn has a gigantic user base, almost as large as TensorFlow's
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
I think they mean deep learning
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Correct me if I’m wrong: TensorFlow is a data structure used for ML while Scikit-learn is an actually ML library, right?
-
No. Both are libraries. Tensorflow is primarily a Deep Learning library, while Scikit learn is primarily a Machine library.
- Show replies
New conversation -
-
-
Most of the time, we spend some to know how the task can be done in tf and keras if we need to apply deep learning, but for production, most models are built with sklean and statsmodel. All because of regulation and easy interpretability of simple models and also team composition
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Ramen!
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
>Scikit-Learn has a gigantic user base, almost as large as TensorFlow's Citation needed. Everyone that I know that use TensorFlow almost always use Scikit-Learn somewhere in their code, not vice-versa.
-
That's just your bubble
End of conversation
New conversation -
-
-
And a much better API (except Keras).
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
PyTorch has a large and growing contingent! Last year, I tried measuring an “ecosystem” score for many frameworks and PyTorch (not v1 at the time) was very close to TFhttps://source.coveo.com/2018/08/14/deep-learning-showdown/#round1 …
-
I switched to PyTorch as soon as I could. My life is now better xD
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.