Here is the same dynamic RNN implemented in 4 different frameworks (TensorFlow/Keras, MXNet/Gluon, Chainer, PyTorch). Can you tell which is which?pic.twitter.com/nsfuTULlKS
Show this thread
-
You'll hear some say, "you can't implement X in framework Y, you need framework Z". It was already nonsense before all frameworks supported the same API style, but it's even more ridiculous now that you can port code from one library to any other with only minor syntax changes
Show this thread
It's in the same category of nonsense as people claiming "you get better accuracy if you implement this model in framework X!" -- the output of an algorithm does not depend on the language you implement it in.
-
-
Tthose frameworks differs only in time of execution (with
@TensorFlow being a little faster than keras, for example)Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
I have seen some implementation differences in some algorithms, which could conceivably lead to different accuracies. It can be due to implementation errors, underspecified algorithms, or different default parameter values.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
At least it had better not!
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Tell that the people who tried research this topics before the CUDA frameworks became available. Be sure to dress with protective clothing before doing so.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Of course framework and language matters when considered in general time and memory consumption _are_ part of any algorithm's properties and its result. We just don't care usually, and you might not see as you compare apples with apples.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
I don’t think is a nonsense. Frameworks have different ways to address mem and compute execution. Accuracy as some level is guarantee but it will differ as well... I have been working on acceleration of nn and accuracy always changes when switching to different frameworks
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.