如何在matconvnet中通过回归更改softmaxlayer [英] how to change softmaxlayer with regression in matconvnet

问题描述

我正在尝试使用单个输出来训练MNIST数据集.这意味着当我输入28 * 28的输入(图像)时，模型会给我们一个公正的数字.例如，我给"5"，模型给我的结果是4.9,5，5.002或接近5.所以我有一些文件红色.人们告诉我们，softmaxlayer必须通过回归层进行更改.为此，请执行此操作.我正在使用matconvnet库及其mnist示例.我更改了网络并编写了回归图层损失函数.这些是我的代码:

I am trying to train MNIST data set with single output. It means when i give an 28*28 input (image) the model gives us a just number. For example i give '5', the model give me as a result 4.9,5, 5.002 or close to 5. So I have red some documents. People tells softmaxlayer have to be changed with regression layer. For doing do this. I am using matconvnet library and its mnist example. I have changed my network and written regression layer loss function. these are my codes:

net.layers = {} ;
net.layers{end+1} = struct('type', 'conv', ...
                           'weights', {{f*randn(5,5,1,20, 'single'), zeros(1, 20, 'single')}}, ...
                           'stride', 1, ...
                           'pad', 0) ;
net.layers{end+1} = struct('type', 'pool', ...
                           'method', 'max', ...
                           'pool', [2 2], ...
                           'stride', 2, ...
                           'pad', 0) ;
net.layers{end+1} = struct('type', 'conv', ...
                           'weights', {{f*randn(5,5,20,50, 'single'),zeros(1,50,'single')}}, ...
                           'stride', 1, ...
                           'pad', 0) ;
net.layers{end+1} = struct('type', 'pool', ...
                           'method', 'max', ...
                           'pool', [2 2], ...
                           'stride', 2, ...
                           'pad', 0) ;
net.layers{end+1} = struct('type', 'conv', ...
                           'weights', {{f*randn(4,4,50,500, 'single'),  zeros(1,500,'single')}}, ...
                           'stride', 1, ...
                           'pad', 0) ;
net.layers{end+1} = struct('type', 'relu') ;
net.layers{end+1} = struct('type', 'conv', ...
                           'weights', {{f*randn(1,1,500,1, 'single'), zeros(1,1,'single')}}, ...
                           'stride', 1, ...
                           'pad', 0) ;                         
 net.layers{end+1} = struct('type', 'normloss');

这是回归损失函数:

function Y = vl_normloss(X,c,dzdy)
size(X)%1 1 1 100
size(c)%1 100

if nargin <= 2

Y = 0.5*sum((squeeze(X)'-c).^2);
size(Y)%1 1
Y      % 1.7361e+03
else
size(Y)
Y = +((squeeze(X)'-c))*dzdy;
Y = reshape(Y,size(X));
end

我将opts.errorFunction = 'multiclass' ;更改为'none' 我还要添加

I changed opts.errorFunction = 'multiclass' ; to 'none' Also i add

case 'normloss'
      res(i+1).x = vl_normloss(res(i).x,l.class) ;

到vl_simplenn脚本

to vl_simplenn script

但是当我跑步训练时会发生此错误

But when i run train this error occurs

使用vl_nnconv的错误DEROUTPUT尺寸与X和 过滤器.

Error using vl_nnconv DEROUTPUT dimensions are incompatible with X and FILTERS.

vl_simplenn中的错误(第415行) [res(i).dzdx，dzdw {1}，dzdw {2}] = ...

Error in vl_simplenn (line 415) [res(i).dzdx, dzdw{1}, dzdw{2}] = ...

解决这个问题我需要做什么?谢谢

what i have to do for solving this problem? thank you

推荐答案

我找到了解决方案.我弄错了.在vl_simplenn脚本中必须更改2行，但是我只更改了一行.该代码有效.

I found the solution. I have made a mistake. There are 2 different line have to be changed in vl_simplenn script but i changed only one line. This code works.

这篇关于如何在matconvnet中通过回归更改softmaxlayer的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！