Training File (xor.data):
4 2 1
-1 -1
-1
-1 1
1
1 -1
1
1 1
-1
<?php
$num_input = 2;
$num_output = 1;
$num_layers = 3;
$num_neurons_hidden = 3;
$desired_error = 0.001;
$max_epochs = 500000;
$epochs_between_reports = 1000;
$training_data = dirname(__FILE__) . "/xor.data"; // training data file
$ann_save_file = dirname(__FILE__) . "/xor_float.net"; // training data file
// Create ANN object using
$ann = fann_create_standard($num_layers, $num_input, $num_neurons_hidden, $num_output);
if ($ann) {
// Configure the ANN Activation Function
fann_set_activation_function_hidden($ann, FANN_SIGMOID_SYMMETRIC);
fann_set_activation_function_output($ann, FANN_SIGMOID_SYMMETRIC);
// Try to train using fann_train_on_file()
if (fann_train_on_file($ann, $training_data, $max_epochs, $epochs_between_reports, $desired_error)){
echo 'xor trained.' . PHP_EOL);
}
// Try to save
if (fann_save($ann, $ann_save_file)){
echo 'xor saved.' . PHP_EOL);
}
// Destroy the $ann object
fann_destroy($ann);
}
?>
fann_train_on_file
(PECL fann >= 1.0.0)
fann_train_on_file — Trains on an entire dataset, which is read from file, for a period of time
Description
fann_train_on_file(
resource
string
int
int
float
): bool
resource
$ann,string
$filename,int
$max_epochs,int
$epochs_between_reports,float
$desired_error): bool
Trains on an entire dataset, which is read from file, for a period of time.
This training uses the training algorithm chosen by fann_set_training_algorithm() and the parameters set for these training algorithms.
Parameters
-
ann -
Neural network resource.
-
filename -
The file containing train data
-
max_epochs -
The maximum number of epochs the training should continue
-
epochs_between_reports -
The number of epochs between calling a user function. A value of zero means that user function is not called.
-
desired_error -
The desired fann_get_MSE() or fann_get_bit_fail(), depending on the stop function chosen by fann_set_train_stop_function()
Return Values
Returns true on success, or false otherwise.
See Also
- fann_train_on_data() - Trains on an entire dataset for a period of time
- fann_train_epoch() - Train one epoch with a set of training data
- fann_get_bit_fail() - The number of fail bits
- fann_get_MSE() - Reads the mean square error from the network
- fann_set_train_stop_function() - Sets the stop function used during training
- fann_set_training_algorithm() - Sets the training algorithm
- fann_set_callback() - Sets the callback function for use during training
add a note
User Contributed Notes 1 note
geekgirljoy at gmail dot com ¶
6 years ago
