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
-
What about changing the graph on the fly, I’ve heard so many people say that pytorch does (dynamic graphing) but tf is static, has this changed / was this ever true? Asking for a friend ; ]
Define-by-run is supported by all 4 APIs above. But unless you're doing advanced NLP research, you likely don't need it, and the drawbacks are significant compared to compiled graphs (performance, etc). "Dynamic is better than static" is just an empty talking point.
-
-
The smarter thing to do is to blend imperative and symbolic paradigms like tf.Keras and Gluon do. You retain the core advantages of compiled graphs in most situations, and you still have access to the flexibility of dynamic graphs when you need it.
-
It should be noted that chainer also supports graph and sub-graph caching for performance optimisation purposes.
End of conversation
New conversation -
-
-
Worth knowing - thank you! I’ve seen it talked about relating to Bayesian NNs, not sure it’s necessary yet, I need to look into it more.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Interesting insight. I have much to learn.
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.