Struct fann::TrainData

pub struct TrainData { /* private fields */ }

Implementations

impl TrainData

pub fn from_file<P: AsRef<Path>>(path: P) -> FannResult<TrainData>

Read a file that stores training data.

The file must be formatted like:

num_train_data num_input num_output
inputdata separated by space
outputdata separated by space
.
.
.
inputdata separated by space
outputdata separated by space

pub fn from_callback( num_data: c_uint, num_input: c_uint, num_output: c_uint, cb: Box<dyn Fn(c_uint) -> (Vec<fann_type>, Vec<fann_type>)> ) -> FannResult<TrainData>

Create training data using the given callback which for each number between 0 (included) and num_data (excluded) returns a pair of input and output vectors with num_input and num_output entries respectively.

pub fn save<P: AsRef<Path>>(&self, path: P) -> FannResult<()>

Save the training data to a file.

pub fn merge(data1: &TrainData, data2: &TrainData) -> FannResult<TrainData>

Merge the given data sets into a new one.

pub fn subset(&self, pos: c_uint, length: c_uint) -> FannResult<TrainData>

Create a subset of the training data, starting at the given positon and consisting of length samples.

pub fn length(&self) -> c_uint

Return the number of training patterns in the data.

pub fn num_input(&self) -> c_uint

Return the number of input values in each training pattern.

pub fn num_output(&self) -> c_uint

Return the number of output values in each training pattern.

pub fn scale_for(&mut self, fann: &Fann) -> FannResult<()>

Scale input and output in the training data using the parameters previously calculated for the given network.

pub fn descale_for(&mut self, fann: &Fann) -> FannResult<()>

Descale input and output in the training data using the parameters previously calculated for the given network.

pub fn scale_input( &mut self, new_min: fann_type, new_max: fann_type ) -> FannResult<()>

Scales the inputs in the training data to the specified range.

pub fn scale_output( &mut self, new_min: fann_type, new_max: fann_type ) -> FannResult<()>

Scales the outputs in the training data to the specified range.

pub fn scale( &mut self, new_min: fann_type, new_max: fann_type ) -> FannResult<()>

Scales the inputs and outputs in the training data to the specified range.

pub fn shuffle(&mut self)

Shuffle training data, randomizing the order. This is recommended for incremental training while it does not affect batch training.

pub unsafe fn get_raw(&self) -> *mut fann_train_data

Get a pointer to the underlying raw fann_train_data structure.

Trait Implementations

impl Clone for TrainData

fn clone(&self) -> TrainData

Returns a copy of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Drop for TrainData

fn drop(&mut self)

Executes the destructor for this type.