lstm的简单实现

最新推荐文章于 2025-11-10 18:11:29 发布

原创

最新推荐文章于 2025-11-10 18:11:29 发布 · 969 阅读

3 ·

CC 4.0 BY-SA版权

文章标签：

#tensorflow

本文详细介绍了长短期记忆网络（LSTM）的实现过程，包括输入门、输出门和遗忘门的运作机制，以及如何使用LSTM进行前向传播和反向传播。通过具体的代码示例，展示了权重初始化、激活函数应用、状态更新等关键步骤。

使用模型

LSTM的结构有很多种形式，但是都大同小异，主要都包含输入门、输出门、遗忘门。

使用模型如上图所示

部分代码


//
//  MLLstm.m
//  LSTM
//

//

#import "MLLstm.h"

@implementation MLLstm

#pragma mark - Inner Method

+ (double)truncated_normal:(double)mean dev:(double)stddev
{
    double outP = 0.0;
    do {
        static int hasSpare = 0;
        static double spare;
        if (hasSpare) {
            hasSpare = 0;
            outP = mean + stddev * spare;
            continue;
        }
        
        hasSpare = 1;
        static double u,v,s;
        do {
            u = (rand() / ((double) RAND_MAX)) * 2.0 - 1.0;
            v = (rand() / ((double) RAND_MAX)) * 2.0 - 1.0;
            s = u * u + v * v;
        } while ((s >= 1.0) || (s == 0.0));
        s = sqrt(-2.0 * log(s) / s);
        spare = v * s;
        outP = mean + stddev * u * s;
    } while (fabsl(outP) > 2*stddev);
    return outP;
}

+ (double *)fillVector:(double)num size:(int)size
{
    double *outP = malloc(sizeof(double) * size);
    vDSP_vfillD(&num, outP, 1, size);
    return outP;
    
}

+ (double *)weight_init:(int)size
{
    double *outP = malloc(sizeof(double) * size);
    for (int i = 0; i < size; i++) {
        outP[i] = [MLLstm truncated_normal:0 dev:0.1];
    }
    return outP;
}

+ (double *)bias_init:(int)size
{
    return [MLLstm fillVector:0.1f size:size];
}

+ (double *)tanh:(double *)input size:(int)size
{
    for (int i = 0; i < size; i++) {
        double num = input[i];
        if (num > 20) {
            input[i] = 1;
        }
        else if (num < -20)
        {
            input[i] = -1;
        }
        else
        {
            input[i] = (exp(num) - exp(-num)) / (exp(num) + exp(-num));
        }
    }
    return input;
}

+ (double *)sigmoid:(double *)input size:(int)size
{
    for (int i = 0; i < size; i++) {
        double num = input[i];
        if (num > 20) {
            input[i] = 1;
        }
        else if (num < -20)
        {
            input[i] = 0;
        }
        else
        {
            input[i] = exp(num) / (exp(num) + 1);
        }
    }
    return input;
}

#pragma mark - Init

- (id)initWithNodeNum:(int)num layerSize:(int)size dataDim:(int)dim
{
    self = [super init];
    if (self) {
        _nodeNum = num;
        _layerSize = size;
        _dataDim = dim;
        [self setupNet];
    }
    return self;
}

- (id)init
{
    self = [super init];
    if (self) {
        [self setupNet];
    }
    return self;
}

- (void)setupNet
{
    _hState = calloc(_layerSize * _nodeNum, sizeof(double));
    _rState = calloc(_layerSize * _nodeNum, sizeof(double));
    _zState