126 lines
2.9 KiB
PHP
126 lines
2.9 KiB
PHP
<?php
|
|
|
|
namespace Rubix\ML\Tests\NeuralNet\Layers;
|
|
|
|
use Tensor\Matrix;
|
|
use Rubix\ML\Deferred;
|
|
use Rubix\ML\NeuralNet\Layers\Noise;
|
|
use Rubix\ML\NeuralNet\Layers\Layer;
|
|
use Rubix\ML\NeuralNet\Layers\Hidden;
|
|
use Rubix\ML\NeuralNet\Optimizers\Stochastic;
|
|
use PHPUnit\Framework\TestCase;
|
|
|
|
/**
|
|
* @group Layers
|
|
* @covers \Rubix\ML\NeuralNet\Layers\Noise
|
|
*/
|
|
class NoiseTest extends TestCase
|
|
{
|
|
protected const RANDOM_SEED = 0;
|
|
|
|
/**
|
|
* @var int
|
|
*/
|
|
protected $fanIn;
|
|
|
|
/**
|
|
* @var \Tensor\Matrix
|
|
*/
|
|
protected $input;
|
|
|
|
/**
|
|
* @var \Rubix\ML\Deferred
|
|
*/
|
|
protected $prevGrad;
|
|
|
|
/**
|
|
* @var \Rubix\ML\NeuralNet\Optimizers\Optimizer
|
|
*/
|
|
protected $optimizer;
|
|
|
|
/**
|
|
* @var \Rubix\ML\NeuralNet\Layers\Noise
|
|
*/
|
|
protected $layer;
|
|
|
|
/**
|
|
* @before
|
|
*/
|
|
protected function setUp() : void
|
|
{
|
|
$this->fanIn = 3;
|
|
|
|
$this->input = Matrix::quick([
|
|
[1., 2.5, -0.1],
|
|
[0.1, 0., 3.],
|
|
[0.002, -6., -0.5],
|
|
]);
|
|
|
|
$this->prevGrad = new Deferred(function () {
|
|
return Matrix::quick([
|
|
[0.25, 0.7, 0.1],
|
|
[0.50, 0.2, 0.01],
|
|
[0.25, 0.1, 0.89],
|
|
]);
|
|
});
|
|
|
|
$this->optimizer = new Stochastic(0.001);
|
|
|
|
$this->layer = new Noise(0.1);
|
|
|
|
srand(self::RANDOM_SEED);
|
|
}
|
|
|
|
/**
|
|
* @test
|
|
*/
|
|
public function build() : void
|
|
{
|
|
$this->assertInstanceOf(Noise::class, $this->layer);
|
|
$this->assertInstanceOf(Layer::class, $this->layer);
|
|
$this->assertInstanceOf(Hidden::class, $this->layer);
|
|
}
|
|
|
|
/**
|
|
* @test
|
|
*/
|
|
public function initializeForwardBackInfer() : void
|
|
{
|
|
$this->layer->initialize($this->fanIn);
|
|
|
|
$this->assertEquals($this->fanIn, $this->layer->width());
|
|
|
|
$expected = [
|
|
[0.9396596259960941, 2.408572590287506, -0.16793207202614419],
|
|
[0.1457098686524435, -0.0783513312152093, 3.063132246060683],
|
|
[-0.08825748362793215, -5.936776081560676, -0.5918333225801408],
|
|
];
|
|
|
|
$forward = $this->layer->forward($this->input);
|
|
|
|
$this->assertInstanceOf(Matrix::class, $forward);
|
|
$this->assertEquals($expected, $forward->asArray());
|
|
|
|
$gradient = $this->layer->back($this->prevGrad, $this->optimizer)->compute();
|
|
|
|
$expected = [
|
|
[0.25, 0.7, 0.1],
|
|
[0.5, 0.2, 0.01],
|
|
[0.25, 0.1, 0.89],
|
|
];
|
|
|
|
$this->assertInstanceOf(Matrix::class, $gradient);
|
|
$this->assertEquals($expected, $gradient->asArray());
|
|
|
|
$expected = [
|
|
[1., 2.5, -0.1],
|
|
[0.1, 0., 3.],
|
|
[0.002, -6., -0.5],
|
|
];
|
|
|
|
$infer = $this->layer->infer($this->input);
|
|
|
|
$this->assertInstanceOf(Matrix::class, $infer);
|
|
$this->assertEquals($expected, $infer->asArray());
|
|
}
|
|
}
|