Google web search interest around deep learning frameworks over time. If you remember Q4 2015 and Q1-2 2016 as confusing, you weren't alone.pic.twitter.com/1f1VQVGr8n
-
Thx for the answer ! For non DeepLearning experts, Keras is enough ? Even for production ? (I feel so, after used both)
Keras+TF is great for prod (see TF Serving). And almost every advanced use case is covered by the Keras API: VAE, GAN, MemNN, you name it
-
-
Great !! When you say Keras+TF ? Does it mean Keras + TF backend or some parts in Keras (whatever backend) and other in TF ?
-
Keras + TF backend, which is really just an easier way to use TF graphs. It gives you access to TF Serving, etc.
- Show replies
New conversation -
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.