Export a neural network trained with MATLAB in other programming languages

Question

kheirou 2014-2-21

1
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/117044-export-a-neural-network-trained-with-matlab-in-other-programming-languages

评论： Lipi Mukherjee 2019-8-26

I trained a NN with matlab using the following code :

    p = [-1 -1 2 2; 0 5 0 5];
    t = [-1 -1 1 1];
    net = newff(p,t,3);
    net = train(net,p,t);
    y = sim(net,p)

Now i'm tring to use the weights & bias calculated by matlab in order to use them to creat a NN in other programming languages, so i used the NN parameters to calculate the output as 'sim function' do :

    input = [-1;0]
    y1 = tansig(netsum(dotprod(net.IW{1} , input) , net.b{1}));
    Results = purelin(netsum(dotprod(net.LW{2} ,y1) ,net.b{2})) 
    Y = sim(net,[-1;0])

By this way i do not the same result ?

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

H. Birkan 2017-3-9

1
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/117044-export-a-neural-network-trained-with-matlab-in-other-programming-languages#answer_258026

在 MATLAB Online 中打开

After digging internet and Matlab documentation, finally reached a solution.

Here I am giving a solution in Matlab, but if you have tanh() function, you may easily convert it to any programming language. It is for just showing the fields from network object and the operations you need.

Assume you have a trained ann (network object) that you want to export
Assume that the name of the trained ann is trained_ann

Here is the script for exporting and testing. Testing script compares original network result with my_ann_evaluation() result % Export IT exported_ann_structure = my_ann_exporter(trained_ann);

% Run and Compare 
% Works only for single INPUT vector
% Please extend it to MATRIX version by yourself
input = [12 3 5 100];
res1 = trained_ann(input')';
res2 = my_ann_evaluation(exported_ann_structure, input')';

where you need the following two functions

First my_ann_exporter:

function [ my_ann_structure ] = my_ann_exporter(trained_netw)
% Just for extracting as Structure object
my_ann_structure.input_ymax = trained_netw.inputs{1}.processSettings{1}.ymax;
my_ann_structure.input_ymin = trained_netw.inputs{1}.processSettings{1}.ymin;
my_ann_structure.input_xmax = trained_netw.inputs{1}.processSettings{1}.xmax;
my_ann_structure.input_xmin = trained_netw.inputs{1}.processSettings{1}.xmin;
my_ann_structure.IW = trained_netw.IW{1};
my_ann_structure.b1 = trained_netw.b{1};
my_ann_structure.LW = trained_netw.LW{2};
my_ann_structure.b2 = trained_netw.b{2};
my_ann_structure.output_ymax = trained_netw.outputs{2}.processSettings{1}.ymax;
my_ann_structure.output_ymin = trained_netw.outputs{2}.processSettings{1}.ymin;
my_ann_structure.output_xmax = trained_netw.outputs{2}.processSettings{1}.xmax;
my_ann_structure.output_xmin = trained_netw.outputs{2}.processSettings{1}.xmin;
end

Second my_ann_evaluation:

function [ res ] = my_ann_evaluation(my_ann_structure, input)
% Works with only single INPUT vector
% Matrix version can be implemented
ymax = my_ann_structure.input_ymax;
ymin = my_ann_structure.input_ymin;
xmax = my_ann_structure.input_xmax;
xmin = my_ann_structure.input_xmin;
input_preprocessed = (ymax-ymin) * (input-xmin) ./ (xmax-xmin) + ymin;
% Pass it through the ANN matrix multiplication
y1 = tanh(my_ann_structure.IW * input_preprocessed + my_ann_structure.b1);
y2 = my_ann_structure.LW * y1 + my_ann_structure.b2;
ymax = my_ann_structure.output_ymax;
ymin = my_ann_structure.output_ymin;
xmax = my_ann_structure.output_xmax;
xmin = my_ann_structure.output_xmin;
res = (y2-ymin) .* (xmax-xmin) /(ymax-ymin) + xmin;
end