RNNSharp
RNNSharp copied to clipboard
(Request) Make code more easy to use
Hello zhongkaifu,
Your framework is very great but there are something I think you should change a little to get your code more easy to use. Can you change your code in the way that it can receive directly a matrix, a jagged array as input, have a train and predict method like here ? (The example)
http://accord-framework.net/docs/html/T_Accord_MachineLearning_VectorMachines_MulticlassSupportVectorMachine.htm
With this change, I think you will make a big milestone.
Regards
Thanks for your suggestion. I'm thinking about refactoring each neural network layer to abstract interface. If you have any idea about it, please let me know. Thanks.