On: Forecasting at Uber with RNNs

[eggie5]

That example is essentially building (and ostensibly training) an albeit a trivial model in Go. Typically you have more complicated architecture so you're deployment has two parts:

* the weights * and the architecture

[nl → eggie5]

Yes, the example is TF Hello World.

But the very first sentence on that page says: These APIs are particularly well-suited to loading models created in Python and executing them within a Go application

This is exactly what Uber is doing.