Question

我在网上找到了一些用PHP完成的神经网络的源代码。您可以在此处找到它：http://pastebin.com/MaqFXkWW

我认为这对于决定你之前画过画布的东西是否合适是完美的。所以我开始构建一个概念证明并构建这个neural_trainer.php脚本：

<? 
require_once ("class_neuralnetwork.php");

$pattern = $_POST['data'];

$n = new NeuralNetwork(90000, 90000, 1);
$n->setVerbose(false);

$n->addTestData($pattern, array (0));

$max = 9;


while (!($success = $n->train(1000, 0.01)) && $max -- > 0) {
    echo "Nothing found...<hr />";
}


if ($success) {
    $epochs = $n->getEpoch();
    echo "Success in $epochs training rounds!<hr />";
}


for ($i = 0; $i < count($n->trainInputs); $i ++) {
    $output = $n->calculate($n->trainInputs[$i]);
    print "<br />Testset $i; ";
    print "expected output = (".implode(", ", $n->trainOutput[$i]).") ";
    print "output from neural network = (".implode(", ", $output).")\n";
}

这是javascript，发布到neural_trainer.php

//canvas1 is 300x300
var img1Data = ctx1.getImageData(0,0,canvas1.width,canvas1.height);

$.ajax({
    url: 'neural_training.php',
    data: { data: img },
    type: 'post',
    success: function(data) {
        console.log(data);
    }
});

但是我一直在抛出Allowed memory size of x bytes exhausted (tried to allocate x bytes)，尽管我把它放在class_neuralnetwork.php ini_set("memory_limit","340M"); ini_set('max_execution_time', 1000);的顶部

Answer 1

PHP可用的内存太小。通过memory_limit配置指令增加PHP可用的内存，或重写脚本使其占用更少的内存。

神经网络无法处理给定的负载

1 个答案: