As of TensorFlow 1.7, with eager execution, you can use a Chainer-like API in tf.keras to create models with dynamic control flow. This should be especially useful for NLP researchers working with recursive models!pic.twitter.com/ZfAs3u0HJ0
-
Really nice! I look forward to adding wrappers for use in spaCy. We already have this underway for PyTorch models :) Is there an easy way to pass in a gradient wrt output to update the graph from a given node? (You don't need to tell me what it is; I can get that from the docs)
Please open a GitHub issue about what you're doing and we can discuss
-
-
I'm sure it'll just be usage we can get from docs -- I wouldn't want to clutter your issues :). We'll want to take the output of a Keras model and feed it forward into some other function. Eventually we'll get a gradient to feed back to keras.
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.