Expand description
The module contains functions, structs, enums, and traits for input/output neural networks. E. g. it can save network to the file and then loads it back.
Example
Saving of neural network:
use neuroflow::FeedForward;
use neuroflow::io;
let mut nn = FeedForward::new(&[2, 2, 1]);
/* train here your neural network */
io::save(&mut nn, "test.flow");
Restoring of neural network:
use neuroflow::FeedForward;
use neuroflow::io;
let mut new_nn: FeedForward = io::load("test.nn")
.unwrap_or(FeedForward::new(&[2, 2, 1]));
Functions
- Loads and restores the neural network from file.
- Saves given neural network to file specified by
file_path
. - Future function for saving in JSON string. return: JSON string