Comment Comment by jph00 Yay, making deep learning uncool again! ;) (http://www.fast.ai/about/)But seriously - does it even make use to have a "define by run" dynamic framework as a backend? It seems to me that keras is particularly suited to wrapping frameworks that define and run a computation graph. parent jph00 9 years ago
But seriously - does it even make use to have a "define by run" dynamic framework as a backend? It seems to me that keras is particularly suited to wrapping frameworks that define and run a computation graph.