You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more
Importantly, in TF 2.0, both of these styles are available and are fully interoperable. You can mix and match models defined with either style. At the end of the day, everything is a Model! That way, you are free to pick the most appropriate API for the task at hand.
In general I expect ~90-95% of use cases to be covered by the Functional API. The Model subclassing API targets deep learning researchers specifically (about 5% of use cases).
I think it's great that we don't silo researchers and everyone else into completely separate frameworks. It's all one API, that enables a spectrum of workflows, from really easy (Sequential) to advanced (Functional) to fully flexible and hackable (Model subclassing)
Is there a way to relax the requirement that loss func take in 2 Tensors of same shape? I have resort to some hack that hurt perf to trade off for some external elegance. If I m wrong, I will be glad to be enlightened.
Just call `layer.add_loss(loss_tensor)` or `model.add_loss(loss_tensor)` with a tensor you've computed yourself
Functional API is the best. Started with Sequential but once you try functional API there is no turning back. It feels so natural to work with it!
Yes, I think this gives you flexibility of not doing a subclass. There r situation where a functional programming approach is better than pure OOP.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
