TensorFlow 2.0 is a machine learning platform from the future. It changes everything.
-
-
Replying to @fchollet
I am in the tiny minority who loved declarative paradigm of tf 1.x It made it very easy to develop on a laptop and just verify that the graph compiles without passing any data through, followed by git push and hand over the training to an AWS instance. The little joys of life.
2 replies 1 retweet 14 likes
Replying to @JaiyamSharma
A Keras functional model validates its graph without needing to be executed.
0 replies
1 retweet
16 likes
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.