前往小程序,Get更优阅读体验!
立即前往
首页
学习
活动
专区
工具
TVP
发布
社区首页 >专栏 >pytorch 移动端框架 thnets 附c示例代码

pytorch 移动端框架 thnets 附c示例代码

作者头像
cpuimage
发布2018-04-12 16:10:15
8480
发布2018-04-12 16:10:15
举报
文章被收录于专栏:算法+算法+

前年年前做一个手机移动端图像识别项目的时候,

先后尝试了mxnet,thnets,caffe,tensorflow.

当时的情况是,mxnet内存管理奇差,内存经常由于模型运算分配不足,app挂掉。

后来调研了下caffe发现也很不友好。

最后发现thnets相对比较轻巧,

经过算法调优之后,性能还不错,

特别是在ios下启用了Accelerate加速库。

后来tensorflow快速发展,就切到tensorflow上了。

最近看了下thnets,作者 mvitez 看来不怎么上心了。

至今为止,改进的不多。

thnets的移动端样例代码,可以参考:

https://github.com/e-lab/apps-iOs

https://github.com/e-lab/apps-android

有一段时间nnpack加速库起来了,就想着把thnets给patch一下nnpack.

但是由于项目太赶,没那个时间去做。

后来也因为切换到tensorflow上了。

thnets就被雪藏了。

向作者提交了两个建议,1,改用stb_image加载图片  2, 支持windows平台

这个两个工作,我都做了。

作者合了1。

2 我关闭了。几天前去看历史记录,作者当时问我关闭的原因,我没回。

真正的原因是。。。thnets被我遗忘了,而windows 版本的存在意义并不大。

今天稍微花了点时间,在windows写个thnets的demo样例,给有需要的网友~

项目地址:

https://github.com/cpuimage/thnets

代码示例见:demo.c

代码语言:javascript
复制
#include <string.h> 
#include <stdlib.h> 
#include <stdio.h> 
#include "thnets.h"
// http://tntmonks.cnblogs.com/
THNETWORK * net;

char * labels[] = { "lamp"," bottle"," watch"," pen"," grass"," shoe"," wall"," chair"," mug"," fork"," table"," book"," tablet"," bookcase"," pencil"," door"," face"," ceiling"," sofa"," bicycle"," aluminum - can"," window"," road"," stairs"," floor"," painting"," toy"," remote"," computer"," plant"," television"," dog"," laptop"," microwave"," cat"," tree"," knife"," car"," motorcycle"," person"," cup"," sidewalk"," telephone"," spoon"," hand"," sofabed" };

int main(int argc, char ** argv) {
    img_t image = { 0 };
    //test.jpg 
    char * pic_file = argv[1];
    //model
    char * model_path = argv[2];

    int dropclassifier = 0;
    loadimage(pic_file, &image);
    THInit();
    printf("init_thnets.");
    net = THLoadNetwork(model_path);
    if (net) {
        THUseSpatialConvolutionMM(net, 2);
        if (dropclassifier == 1) {
            if (net->net->modules[net->net->nelem - 1].type == MT_SoftMax)
                net->net->nelem--;
            if (net->net->modules[net->net->nelem - 1].type == MT_Linear)
                net->net->nelem--;
            if (net->net->modules[net->net->nelem - 1].type == MT_View)
                net->net->nelem--;
        }
    }
    else {
        printf("Shiiiiit went down.");
        return -1;
    }
    float * percentages = 0;
    int outwidth, outheight;

    if (!net) {
        return 0;
    }
    int i = 0;
    int nbatch = 1;
    unsigned char *bitmaps[256];
    for (i = 0; i < nbatch; i++)
        bitmaps[i] = image.bitmap;
    int size = THProcessImages(net, bitmaps, nbatch, image.width, image.height, image.cp * image.width, &percentages, &outwidth, &outheight, 0);
    for (i = 0; i < nbatch; i++)
        if (bitmaps[i])
            free(bitmaps[i]);
    if (percentages)
    {
        float max[3] = { 0 };
        int maxPos[3] = { 0 };
        for (int j = 0; j < size; j++) {
            if (percentages[j] > max[0]) {
                maxPos[0] = j;
                max[0] = percentages[j];
            }
            else if (percentages[j] > max[1]) {
                maxPos[1] = j;
                max[1] = percentages[j];
            }
            else if (percentages[j] > max[2]) {
                maxPos[2] = j;
                max[2] = percentages[j];
            }
        }
        for (int index = 0; index < 3; index += 1) {
            const float predictionValue = max[index];
            if (predictionValue > 0.05f) {
                printf(" %f %s  \n", predictionValue, labels[maxPos[index] % size]);
            }
        }
        free(percentages);
    }
    getchar();
}

采用vs编译的话,需要下载openblas:

https://jaist.dl.sourceforge.net/project/openblas/v0.2.19/

lib库链接文件:libopenblas.dll.a 即可编译。

附带的模型 来自e-lab的项目。

示例输出得分最高并且高于0.05的三个结果。

示例图片:test.jpg

示例模型:  model

对应的标签,见代码或模型文件夹下的categories.txt

以上,待有精力再对thnets进行性能调优。

对于前向传播而言,最好的代码学习资料莫过于:darknet

https://github.com/pjreddie/darknet

darknet 代码写得十分耐看,逻辑清晰。

darknet+nnpack:

https://github.com/digitalbrain79/darknet-nnpack

若有其他相关问题或者需求也可以邮件联系俺探讨。

邮箱地址是:  gaozhihan@vip.qq.com

本文参与 腾讯云自媒体分享计划,分享自作者个人站点/博客。
原始发表:2018-01-27 ,如有侵权请联系 cloudcommunity@tencent.com 删除

本文分享自 作者个人站点/博客 前往查看

如有侵权,请联系 cloudcommunity@tencent.com 删除。

本文参与 腾讯云自媒体分享计划  ,欢迎热爱写作的你一起参与!

评论
登录后参与评论
0 条评论
热度
最新
推荐阅读
领券
问题归档专栏文章快讯文章归档关键词归档开发者手册归档开发者手册 Section 归档