PyTorch has a lot of marketing firepower behind it, and as a result there's a common misconception that it has "momentum". Does it? I can't tell for sure, but the handful of traction indicators I monitor are showing that its user base has likely peaked around April-May 2018https://twitter.com/vincenzomanzoni/status/1047561148990730246 …
-
-
This Tweet is unavailable.
-
Precisely -- people who need these capabilities can use tf.keras and eager execution. It has seen a lot of effort, which doesn't need to be duplicated with a more niche framework. However I think for 95% of cases this doesn't help Keras users
End of conversation
-
-
-
This Tweet is unavailable.
-
If it were open-source, possibly. In its current state, I doubt it.
End of conversation
-
-
-
Context? Makes no sense because you work for Google? Is this technical or political?
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.