It is possible to save an entire ann to a file with fann_save for future loading with fann_create_from_file.
| FANN File Input/ | It is possible to save an entire ann to a file with fann_save for future loading with fann_create_from_file. |
| File Input and Output | |
| fann_create_from_file | Constructs a backpropagation neural network from a configuration file, which have been saved by fann_save. |
| fann_save | Save the entire network to a configuration file. |
| fann_save_to_fixed | Saves the entire network to a configuration file. |
FANN_EXTERNAL struct fann *FANN_API fann_create_from_file( const char * configuration_file )
Constructs a backpropagation neural network from a configuration file, which have been saved by fann_save.
This function appears in FANN >= 1.0.0.
FANN_EXTERNAL int FANN_API fann_save( struct fann * ann, const char * configuration_file )
Save the entire network to a configuration file.
The configuration file contains all information about the neural network and enables fann_create_from_file to create an exact copy of the neural network and all of the parameters associated with the neural network.
These three parameters (fann_set_callback, fann_set_error_log, fann_set_user_data) are NOT saved to the file because they cannot safely be ported to a different location. Also temporary parameters generated during training like fann_get_MSE is not saved.
The function returns 0 on success and -1 on failure.
fann_create_from_file, fann_save_to_fixed
This function appears in FANN >= 1.0.0.
FANN_EXTERNAL int FANN_API fann_save_to_fixed( struct fann * ann, const char * configuration_file )
Saves the entire network to a configuration file. But it is saved in fixed point format no matter which format it is currently in.
This is usefull for training a network in floating points, and then later executing it in fixed point.
The function returns the bit position of the fix point, which can be used to find out how accurate the fixed point network will be. A high value indicates high precision, and a low value indicates low precision.
A negative value indicates very low precision, and a very strong possibility for overflow. (the actual fix point will be set to 0, since a negative fix point does not make sence).
Generally, a fix point lower than 6 is bad, and should be avoided. The best way to avoid this, is to have less connections to each neuron, or just less neurons in each layer.
The fixed point use of this network is only intended for use on machines that have no floating point processor, like an iPAQ. On normal computers the floating point version is actually faster.
fann_create_from_file, fann_save
This function appears in FANN >= 1.0.0.
Save the entire network to a configuration file.
FANN_EXTERNAL int FANN_API fann_save( struct fann * ann, const char * configuration_file )
Constructs a backpropagation neural network from a configuration file, which have been saved by fann_save.
FANN_EXTERNAL struct fann *FANN_API fann_create_from_file( const char * configuration_file )
Saves the entire network to a configuration file.
FANN_EXTERNAL int FANN_API fann_save_to_fixed( struct fann * ann, const char * configuration_file )
Sets the callback function for use during training.
FANN_EXTERNAL void FANN_API fann_set_callback( struct fann * ann, fann_callback_type callback )
Change where errors are logged to.
FANN_EXTERNAL void FANN_API fann_set_error_log( struct fann_error * errdat, FILE * log_file )
Store a pointer to user defined data.
FANN_EXTERNAL void FANN_API fann_set_user_data( struct fann * ann, void * user_data )
Reads the mean square error from the network.
FANN_EXTERNAL float FANN_API fann_get_MSE( struct fann * ann )