fann_scale_input

(PECL fann >= 1.0.0)

fann_scale_input — 在以前计算参数的基础上，在训练之前放大输入向量中的数据

说明

fann_scale_input(resource $ann, array $input_vector): bool

在以前计算参数的基础上，在训练之前放大输入向量中的数据。

参数

ann: 神经网络资源。
input_vector: 将要被缩放的输入向量。

返回值

成功时返回 true，其它情况下返回 false。

参见

fann_descale_input() - 在获取基于先前计算的参数之后，在输入向量中缩小数据
fann_scale_output() - 在以前计算参数的基础上，在训练之前放大输出向量中的数据

add a note

User Contributed Notes 4 notes

down

geekgirl dot joy at gmail dot com ¶

1 year ago


<?php

// This example will use the XOR dataset with negative one represented 
// as zero and one represented as one-hundred and demonstrate how to
// scale those values so that FANN can understand them and then how 
// to de-scale the value FANN returns so that you can understand them.

// Scaling allows you to take raw data numbers like -1234.975 or 4502012 
// in your dataset and convert them into an input/output range that
// your neural network can understand. 

// De-scaling lets you take the scaled data and convert it back into 
// the original range.

// scale_test.data
// Note the values are "raw" or un-scaled.
/*
4 2 1
0 0
0
0 100
100
100 0
100
100 100
0
*/

////////////////////
// Configure ANN  //
////////////////////

// New ANN
$ann = fann_create_standard_array(3, [2,3,1]);

// Set activation functions
fann_set_activation_function_hidden($ann, FANN_SIGMOID_SYMMETRIC);
fann_set_activation_function_output($ann, FANN_SIGMOID_SYMMETRIC);

// Read raw (un-scaled) training data from file
$train_data = fann_read_train_from_file("scale_test.data");

// Scale the data range to -1 to 1
fann_set_input_scaling_params($ann , $train_data, -1, 1);
fann_set_output_scaling_params($ann , $train_data, -1, 1);

///////////
// Train //
///////////

// Presumably you would train here (uncomment to perform training)...

// fann_train_on_data($ann, $train_data, 100, 10, 0.01);

// But it's not needed to test the scaling because the training file 
// in this case is just used to compute/derive the scale range. 
// However, doing the training will improve the answer the ANN gives
// in correlation to the training data.

//////////
// Test //
//////////

$raw_input = array(0, 100); // test XOR (0,100) input
$scaled_input = fann_scale_input ($ann , $raw_input); // scaled XOR (-1,1) input
$descaled_input = fann_descale_input ($ann , $scaled_input); // de-scaled XOR (0,100) input
$raw_output = fann_run($ann, $scaled_input); // get the answer/output from the ANN
$output_descale = fann_descale_output($ann, $raw_output); // de-scale the output 

////////////////////
// Report Results //
////////////////////
echo 'The raw_input:' . PHP_EOL;
var_dump($raw_input); 

echo 'The raw_input Scaled then De-Scaled (values are unchanged/correct):' . PHP_EOL;
var_dump($descaled_input); 

echo 'The Scaled input:' . PHP_EOL;
var_dump($scaled_input); 

echo "The raw_output of the ANN (Scaled input):" . PHP_EOL;
var_dump($raw_output);

echo 'The De-Scaled output:' . PHP_EOL;
var_dump($output_descale); 


////////////////////
// Example Output //
////////////////////

 /*
The raw_input:
array(2) {
  [0]=>
  float(0)
  [1]=>
  float(100)
}
The raw_input Scaled then De-Scaled (values are unchanged/correct):
array(2) {
  [0]=>
  float(0)
  [1]=>
  float(100)
}
The Scaled input:
array(2) {
  [0]=>
  float(-1)
  [1]=>
  float(1)
}
The raw_output of the ANN (Scaled input):
array(1) {
  [0]=>
  float(1)
}
The De-Scaled output:
array(1) {
  [0]=>
  float(100)
}
*/

down

geekgirl dot joy at gmail dot com ¶

1 year ago


<?php

// This example will use the XOR dataset with negative one represented 
// as zero and one represented as one-hundred and demonstrate how to
// scale those values so that FANN can understand them and then how 
// to de-scale the value FANN returns so that you can understand them.

// Scaling allows you to take raw data numbers like -1234.975 or 4502012 
// in your dataset and convert them into an input/output range that
// your neural network can understand. 

// De-scaling lets you take the scaled data and convert it back into 
// the original range.

// scale_test.data
// Note the values are "raw" or un-scaled.
/*
4 2 1
0 0
0
0 100
100
100 0
100
100 100
0
*/

////////////////////
// Configure ANN  //
////////////////////

// New ANN
$ann = fann_create_standard_array(3, [2,3,1]);

// Set activation functions
fann_set_activation_function_hidden($ann, FANN_SIGMOID_SYMMETRIC);
fann_set_activation_function_output($ann, FANN_SIGMOID_SYMMETRIC);

// Read raw (un-scaled) training data from file
$train_data = fann_read_train_from_file("scale_test.data");

// Scale the data range to -1 to 1
fann_set_input_scaling_params($ann , $train_data, -1, 1);
fann_set_output_scaling_params($ann , $train_data, -1, 1);

///////////
// Train //
///////////

// Presumably you would train here (uncomment to perform training)...

// fann_train_on_data($ann, $train_data, 100, 10, 0.01);

// But it's not needed to test the scaling because the training file 
// in this case is just used to compute/derive the scale range. 
// However, doing the training will improve the answer the ANN gives
// in correlation to the training data.

//////////
// Test //
//////////

$raw_input = array(0, 100); // test XOR (0,100) input
$scaled_input = fann_scale_input ($ann , $raw_input); // scaled XOR (-1,1) input
$descaled_input = fann_descale_input ($ann , $scaled_input); // de-scaled XOR (0,100) input
$raw_output = fann_run($ann, $scaled_input); // get the answer/output from the ANN
$output_descale = fann_descale_output($ann, $raw_output); // de-scale the output 

////////////////////
// Report Results //
////////////////////
echo 'The raw_input:' . PHP_EOL;
var_dump($raw_input); 

echo 'The raw_input Scaled then De-Scaled (values are unchanged/correct):' . PHP_EOL;
var_dump($descaled_input); 

echo 'The Scaled input:' . PHP_EOL;
var_dump($scaled_input); 

echo "The raw_output of the ANN (Scaled input):" . PHP_EOL;
var_dump($raw_output);

echo 'The De-Scaled output:' . PHP_EOL;
var_dump($output_descale); 


////////////////////
// Example Output //
////////////////////

 /*
The raw_input:
array(2) {
  [0]=>
  float(0)
  [1]=>
  float(100)
}
The raw_input Scaled then De-Scaled (values are unchanged/correct):
array(2) {
  [0]=>
  float(0)
  [1]=>
  float(100)
}
The Scaled input:
array(2) {
  [0]=>
  float(-1)
  [1]=>
  float(1)
}
The raw_output of the ANN (Scaled input):
array(1) {
  [0]=>
  float(1)
}
The De-Scaled output:
array(1) {
  [0]=>
  float(100)
}
*/

down

saakyanalexandr at gmail dot com ¶

2 years ago


fann_scale_input and fann_scale_output return not bool value. This function return scaling vector.

Example
$r = fann_scale_input($ann, $input);
$output = fann_run($ann, $input);
$s = fann_scale_output ( $ann, $output);

$r and $s is array

down

-1

Nolife ¶

4 years ago


Please note -> ALLfann  scaling related functions are not functional.
They are implemented wrong so the scaling is calculated within the library but it's not referenced back to the input variables.

add a note

官方地址：https://www.php.net/manual/en/function.fann-scale-input.php

有任何技术问题请点击这里网站运营推广招聘

IT PHP 编程语言 Linux 开发编程科技 Elasticsearch HTML/CSS/XML 网络 JAVA NoSQL 数据库面试 C/C++ Golang Git 算法操作系统正则表达式 Redis 互联网 MySql JavaScript 运维软件国际架构设计 Mac OS TCP/IP Excel Vim Windows Socket Oracle VR MongoDB Python 运营 MemCache 商业硬件电子娱乐设计 nginx 摄影游戏 WordPress HTTP 团建数码电器

php7 安装fileinfo扩展 preg_split — 通过一个正则表达式分隔字符串 php位值,解决 PHP 中 usort 在值相同时改变原始位置的问题 [PHP] inet_pton/inet_ntop IP地址转换函数 array_multisort() 多字段排序 PHPMailer设置utf8 PHPMailer字符集CharSet ADORecordSet对象 adodb手册 PHP 8.1 [鸟哥]PHP_INT_MIN 和 -9223372036854775808 opcache预加载 Composer的Packagist资源 mysql面试题 [鸟哥]PHP FFI详解 - 一种全新的PHP扩展方式 PHP7添加redis扩展 PHP mkdir()写出来的权限与mode值不符合 Packagist / Composer 中国全量镜像 PHP获取指定函数定义在哪个文件中及行号支持php7的性能采集扩展 adodb连接mysql多个数据库的问题

略微加速

PHP官方手册 - 互联网笔记

fann_scale_input

说明

参数

返回值

参见

User Contributed Notes 4 notes