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
— François Chollet (@fchollet) March 31, 2018
from Twitter https://twitter.com/fchollet
March 30, 2018 at 06:28PM
via IFTTT
No comments:
Post a Comment