fann_subset_train_data

(PECL fann >= 1.0.0)

fann_subset_train_data — Returns an copy of a subset of the train data

Description

fann_subset_train_data(resource $data, int $pos, int $length): resource

Returns an copy of a subset of the train data resource, starting at position pos and length elements forward.

The fann_subset_train_data(train_data, 0, fann_length_train_data(train_data)) do the same as fann_duplicate_train_data()

Parameters

data: Neural network training data resource.
pos: Starting position.
length: The number of copied elements.

Return Values

Returns a train data resource on success, or false on error.

Improve This Page

Learn How To Improve This Page • Submit a Pull Request • Report a Bug

＋add a note

User Contributed Notes 1 note

down

geekgirl dot joy at gmail dot com ¶

5 years ago

<?php
// Use this code to split your data into smaller sets.
// Useful for splitting your training data into training and testing groups

// Load Data
$data_file = "MyTrainingData.data";
$train_data = fann_read_train_from_file(dirname(__FILE__)  .  DIRECTORY_SEPARATOR  .  $data_file);

// Calculate how many examples are in the first group
$total_length = fann_length_train_data($train_data);
$a_length = floor($total_length / 10);

// Split the subsets
$training_data_a  = fann_subset_train_data($train_data, 0, $a_length);
$training_data_b  = fann_subset_train_data($train_data, $a_length, $total_length-$a_length);

// Save the training data to separate files
fann_save_train ($training_data_a, 'MyTrainingData_Subset_A.data'); // 1/10 of the training data
fann_save_train ($training_data_b, 'MyTrainingData_Subset_B.data'); // 9/10 of the training data