Open raghakot opened 7 years ago
All we need is iteration over layers, ability to take gradients with respect to some input in a graph, and abstractions for common keras backend calls.
It might be possible to make the lib support pytorch once these abstractions are in place.
All we need is iteration over layers, ability to take gradients with respect to some input in a graph, and abstractions for common keras backend calls.
It might be possible to make the lib support pytorch once these abstractions are in place.