You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more
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
This API style was initially introduced by Chainer in 2015, and in 2017 multiple other frameworks adopted it (including those listed above). In the context of Keras, I call it "the Model subclassing API". It's a good fit for NLP research in particular!
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 
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.
The lower left version (PyTorch I think) overwrites the first layer in the constuctor, so not quite the same
MXNet, Keras, pytorch, chainer? Left -> right
I'm just a beginner so going to assume from "Block" - "Gluon" "Model" - "keras (tf backend)" "Module" - "torch" "Chain" - "Chainer"??
I love this. It's like @EdwardTufte's small multiples, but with code. 
And with a typo :p
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
