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
Описание
bool fann_train_on_file
( resource
$ann
, string $filename
, int $max_epochs
, int $epochs_between_reports
, float $desired_error
)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.
Список параметров
-
ann -
Ресурс (resource) нейронной сети.
-
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()
Возвращаемые значения
Возвращает TRUE в случае успешного выполнения, или FALSE в противном случае.
Смотрите также
- 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
- PHP Руководство
- Функции по категориям
- Индекс функций
- Справочник функций
- Другие базовые расширения
- FANN (Fast Artificial Neural Network)
- fann_cascadetrain_on_data
- fann_cascadetrain_on_file
- fann_clear_scaling_params
- fann_copy
- fann_create_from_file
- fann_create_shortcut_array
- fann_create_shortcut
- fann_create_sparse_array
- fann_create_sparse
- fann_create_standard_array
- fann_create_standard
- fann_create_train_from_callback
- fann_create_train
- fann_descale_input
- fann_descale_output
- fann_descale_train
- fann_destroy_train
- fann_destroy
- fann_duplicate_train_data
- fann_get_activation_function
- fann_get_activation_steepness
- fann_get_bias_array
- fann_get_bit_fail_limit
- fann_get_bit_fail
- fann_get_cascade_activation_functions_count
- fann_get_cascade_activation_functions
- fann_get_cascade_activation_steepnesses_count
- fann_get_cascade_activation_steepnesses
- fann_get_cascade_candidate_change_fraction
- fann_get_cascade_candidate_limit
- fann_get_cascade_candidate_stagnation_epochs
- fann_get_cascade_max_cand_epochs
- fann_get_cascade_max_out_epochs
- fann_get_cascade_min_cand_epochs
- fann_get_cascade_min_out_epochs
- fann_get_cascade_num_candidate_groups
- fann_get_cascade_num_candidates
- fann_get_cascade_output_change_fraction
- fann_get_cascade_output_stagnation_epochs
- fann_get_cascade_weight_multiplier
- fann_get_connection_array
- fann_get_connection_rate
- fann_get_errno
- fann_get_errstr
- fann_get_layer_array
- fann_get_learning_momentum
- fann_get_learning_rate
- fann_get_MSE
- fann_get_network_type
- fann_get_num_input
- fann_get_num_layers
- fann_get_num_output
- fann_get_quickprop_decay
- fann_get_quickprop_mu
- fann_get_rprop_decrease_factor
- fann_get_rprop_delta_max
- fann_get_rprop_delta_min
- fann_get_rprop_delta_zero
- fann_get_rprop_increase_factor
- fann_get_sarprop_step_error_shift
- fann_get_sarprop_step_error_threshold_factor
- fann_get_sarprop_temperature
- fann_get_sarprop_weight_decay_shift
- fann_get_total_connections
- fann_get_total_neurons
- fann_get_train_error_function
- fann_get_train_stop_function
- fann_get_training_algorithm
- fann_init_weights
- fann_length_train_data
- fann_merge_train_data
- fann_num_input_train_data
- fann_num_output_train_data
- fann_print_error
- fann_randomize_weights
- fann_read_train_from_file
- fann_reset_errno
- fann_reset_errstr
- fann_reset_MSE
- fann_run
- fann_save_train
- fann_save
- fann_scale_input_train_data
- fann_scale_input
- fann_scale_output_train_data
- fann_scale_output
- fann_scale_train_data
- fann_scale_train
- fann_set_activation_function_hidden
- fann_set_activation_function_layer
- fann_set_activation_function_output
- fann_set_activation_function
- fann_set_activation_steepness_hidden
- fann_set_activation_steepness_layer
- fann_set_activation_steepness_output
- fann_set_activation_steepness
- fann_set_bit_fail_limit
- fann_set_callback
- fann_set_cascade_activation_functions
- fann_set_cascade_activation_steepnesses
- fann_set_cascade_candidate_change_fraction
- fann_set_cascade_candidate_limit
- fann_set_cascade_candidate_stagnation_epochs
- fann_set_cascade_max_cand_epochs
- fann_set_cascade_max_out_epochs
- fann_set_cascade_min_cand_epochs
- fann_set_cascade_min_out_epochs
- fann_set_cascade_num_candidate_groups
- fann_set_cascade_output_change_fraction
- fann_set_cascade_output_stagnation_epochs
- fann_set_cascade_weight_multiplier
- fann_set_error_log
- fann_set_input_scaling_params
- fann_set_learning_momentum
- fann_set_learning_rate
- fann_set_output_scaling_params
- fann_set_quickprop_decay
- fann_set_quickprop_mu
- fann_set_rprop_decrease_factor
- fann_set_rprop_delta_max
- fann_set_rprop_delta_min
- fann_set_rprop_delta_zero
- fann_set_rprop_increase_factor
- fann_set_sarprop_step_error_shift
- fann_set_sarprop_step_error_threshold_factor
- fann_set_sarprop_temperature
- fann_set_sarprop_weight_decay_shift
- fann_set_scaling_params
- fann_set_train_error_function
- fann_set_train_stop_function
- fann_set_training_algorithm
- fann_set_weight_array
- fann_set_weight
- fann_shuffle_train_data
- fann_subset_train_data
- fann_test_data
- fann_test
- fann_train_epoch
- fann_train_on_data
- fann_train_on_file
- fann_train
Коментарии
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);
}
?>