fann_train_epoch

(PECL fann >= 1.0.0)

fann_train_epochTrain one epoch with a set of training data

Beschreibung

fann_train_epoch(resource $ann, resource $data): float

Train one epoch with the training data stored in data. One epoch is where all of the training data is considered exactly once.

This function returns the MSE error as it is calculated either before or during the actual training. This is not the actual MSE after the training epoch, but since calculating this will require to go through the entire training set once more. It is more than adequate to use this value during training.

The training algorithm used by this function is chosen by fann_set_training_algorithm() function.

Parameter-Liste

ann

Ressource eines neuralen Netzwerks.

data

Ressource für Trainingsdaten eines neuralen Netzwerks.

Rückgabewerte

The MSE, or false on error.

Siehe auch

add a note add a note

User Contributed Notes 1 note

up
3
geekgirljoy at gmail dot com
5 years ago
This code demonstrates training XOR using fann_train_epoch and will let you watch the training process by observing a psudo MSE (mean squared error).

Other training functions: fann_train_on_data, fann_train_on_file, fann_train.

fann_train_epoch is useful when you want to observe the ANN while it is training and perhaps save snapshots or compare competing networks during training.

fann_train_epoch is different from fann_train in that it takes a data resource (training file) whereas fann_train takes an array of inputs and a separate array of outputs so use fann_train_epoch for observing training on data files (callback training resources) and use fann_train when observing manually specified data.

Example code:

<?php
$num_input
= 2;
$num_output = 1;
$num_layers = 3;
$num_neurons_hidden = 3;
$desired_error = 0.0001;
$max_epochs = 500000;
$current_epoch = 0;
$epochs_between_saves = 100; // Minimum number of epochs between saves
$epochs_since_last_save = 0;
$filename = dirname(__FILE__) . "/xor.data";

// Initialize psudo mse (mean squared error) to a number greater than the desired_error
// this is what the network is trying to minimize.
$psudo_mse_result = $desired_error * 10000; // 1
$best_mse = $psudo_mse_result; // keep the last best seen MSE network score here

// Initialize ANN
$ann = fann_create_standard($num_layers, $num_input, $num_neurons_hidden, $num_output);

if (
$ann) {
  echo
'Training ANN... ' . PHP_EOL;
 
 
// Configure the ANN
 
fann_set_training_algorithm ($ann , FANN_TRAIN_BATCH);
 
fann_set_activation_function_hidden($ann, FANN_SIGMOID_SYMMETRIC);
 
fann_set_activation_function_output($ann, FANN_SIGMOID_SYMMETRIC);
 
 
// Read training data
 
$train_data = fann_read_train_from_file($filename);
 
 
 
// Check if psudo_mse_result is greater than our desired_error
  // if so keep training so long as we are also under max_epochs
 
while(($psudo_mse_result > $desired_error) && ($current_epoch <= $max_epochs)){
   
$current_epoch++;
   
$epochs_since_last_save++; 
 
   
// See: http://php.net/manual/en/function.fann-train-epoch.php
    // Train one epoch with the training data stored in data.
    //
    // One epoch is where all of the training data is considered
    // exactly once.
    //
    // This function returns the MSE error as it is calculated
    // either before or during the actual training. This is not the
    // actual MSE after the training epoch, but since calculating this
    // will require to go through the entire training set once more.
    // It is more than adequate to use this value during training.
   
$psudo_mse_result = fann_train_epoch ($ann , $train_data );
    echo
'Epoch ' . $current_epoch . ' : ' . $psudo_mse_result . PHP_EOL; // report
   
   
    // If we haven't saved the ANN in a while...
    // and the current network is better then the previous best network
    // as defined by the current MSE being less than the last best MSE
    // Save it!
   
if(($epochs_since_last_save >= $epochs_between_saves) && ($psudo_mse_result < $best_mse)){
     
     
$best_mse = $psudo_mse_result; // we have a new best_mse
     
      // Save a Snapshot of the ANN
     
fann_save($ann, dirname(__FILE__) . "/xor.net");
      echo
'Saved ANN.' . PHP_EOL; // report the save
     
$epochs_since_last_save = 0; // reset the count
   
}
 
  }
// While we're training

 
echo 'Training Complete! Saving Final Network.'  . PHP_EOL;
 
 
// Save the final network
 
fann_save($ann, dirname(__FILE__) . "/xor.net"); 
 
fann_destroy($ann); // free memory
}
echo
'All Done!' . PHP_EOL;
?>
To Top