CascadiaPHP 2024


(PECL fann >= 1.0.0)



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

使用保存在 data 中训练数据训练一个周期。一个训练周期表示所有的训练数据正好使用了一次。

这个函数将会返回在其实际计算之前或当中被计算的 MSE 错误。但是因为计算需要再次走一遍整个训练集,所有训练周期之后的不是真正的 MSE。 在训练中使用这个值是绰绰有余的。

该函数使用的是被 fann_set_training_algorithm() 函数选中的训练算法。



神经网络 资源


神经网络训练数据 资源


成功,则返回 MSE, 错误则返回 false .


add a note

User Contributed Notes 1 note

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:

= 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__) . "/";

// 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) {
'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)){

// See:
// 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 );
'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__) . "/");
'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($ann, dirname(__FILE__) . "/");
fann_destroy($ann); // free memory
'All Done!' . PHP_EOL;
To Top