I am using the loadJason routine to load the saved neural network, but the code crashes at the function call. Is there an alternative to load an existing network from hard disk.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
I would need more information to determine the cause of the problem. I recommend building with debug symbols (make dbg), and then running inside a debugger. A call stack would provide a lot of information. If it is throwing an exception, put a breakpoint in Ex::setMessage in GError.cpp to get a call stack to the point where the exception is thrown.
The "waffles_learn test" tool loads a model from a json file (waffles/src/learn/main.cpp). It might be helpful to see how your implementation differs from that one.
Mike
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
I am using the loadJason routine to load the saved neural network, but the code crashes at the function call. Is there an alternative to load an existing network from hard disk.
I would need more information to determine the cause of the problem. I recommend building with debug symbols (make dbg), and then running inside a debugger. A call stack would provide a lot of information. If it is throwing an exception, put a breakpoint in Ex::setMessage in GError.cpp to get a call stack to the point where the exception is thrown.
The "waffles_learn test" tool loads a model from a json file (waffles/src/learn/main.cpp). It might be helpful to see how your implementation differs from that one.
Mike