This was true for your Keras models in 2016, and it is just as true today.
Show this thread
Creating a deep learning model today is an investment in the future. Keras models are appreciating assets: in a few years, you will still be able to run the exact same code/savefile, but it will run much faster and on wider range of platforms.
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
How is it appreciating ? I feel every model I make will be obsolete in the future, in term of performances
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
It takes always time to evolve, if we build deep learning models today, we will have evolved models in future.
#DeepLearningThanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
This Tweet is unavailable.
-
Stop complaining open a free collab notebook and select free gpu / tpu
- Show replies
-
-
-
Even better when we continue to train the model on new real life data?
@AgileStacks provides reusable ML pipeline templates, to deploy models into production as soon as possible. The model will get smarter over time,Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Quite good parody François ...
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
That's only if you Keras to do it!
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Cool
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
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.