Deep Learning Error - how to fix code?

Question

Manny 2024-2-27

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/2087696-deep-learning-error-how-to-fix-code

回答： Venu 2024-3-7

在 MATLAB Online 中打开

I am using this link to implement a deep learning algorithim:

https://www.mathworks.com/help/deeplearning/ref/narnet.html

I followed most of the steps but modified slightly to fit my data. I am getting an error. How do I fix it?

Here is my code:

    FilteredCIV = CIV(strcmp(CIV.SYMBOL,UnderlyingSymbols.SYMBOL(i)),:);
    FilteredCIV = FilteredCIV(FilteredCIV{:,2} <= datenum(2024,2,5),:);
    FilteredCIVOnly = table2array(FilteredCIV(:,"COMPOSITE_IMPLIED_VOLATILITY"));
    
    net = narnet(1:2,10,'none','trainbr');
    [Xs,Xi,Ai,Ts] = preparets(net,{},{},FilteredCIVOnly);
    net = train(net,Xs,Ts,Xi,Ai);
    [Y,Xf,Af] = net(Xs,Xi,Ai);
    [netc,Xic,Aic] = closeloop(net,Xf,Af);
    Yc = netc(cell(0,20),Xic,Aic);

Here is CIV table:

    >> CIV
CIV =
  2452×3 table
    SYMBOL     TRADE_DATE    COMPOSITE_IMPLIED_VOLATILITY
    _______    __________    ____________________________
    {'SPX'}    7.3585e+05               12.596           
    {'SPX'}    7.3585e+05               13.243           
    {'SPX'}    7.3585e+05               13.868           
    {'SPX'}    7.3585e+05               13.621           
    {'SPX'}    7.3585e+05               14.706           

Here is error:

 Index in position 2 exceeds array bounds. Index must not exceed 1.
Error in preparets (line 317)
xi = xx(:,FBS+((1-net.numInputDelays):0));
Error in ForecastModel (line 58)
    [Xs,Xi,Ai,Ts] = preparets(net,{},{},FilteredCIVOnly);

Thank you

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

Venu 2024-3-7

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/2087696-deep-learning-error-how-to-fix-code#answer_1422526

Hi @Manny,

To pass the data properly to preparets, make these two adjustments in your code.

Pass FilteredCIVOnly as a cell array; FilteredCIVOnlyCell = num2cell(FilteredCIVOnly);
Transpose FilteredCIVOnlyCell to ensure that the data is correctly interpreted as a sequence of timesteps by the function; [Xs,Xi,Ai,Ts] = preparets(net, {}, {}, FilteredCIVOnlyCell');

Hope this helps!