i have data.mat file and I am working on load forecasting for solar power with CNN, I am facing issue in data preparation.

Question

muhammad 2023-5-4

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1958264-i-have-data-mat-file-and-i-am-working-on-load-forecasting-for-solar-power-with-cnn-i-am-facing-issu

回答： Govind KM 2024-9-24，10:16

i have data.mat file and I am working on load forecasting for solar power. there are 23 features in my array with each feature has sample size of 4348. This data file is represented as 4348*24, where 24 th column is represented as output. i am want to write CNN code for it. This is my code but I am receving this error.

Error using reshape

Number of elements must not change. Use [] as one of the size inputs to automatically

calculate the appropriate size for that dimension.

Error in CNN (line 15)

X_reshaped = reshape(X_padded, [num_padded_rows/144, 8, 3, 3, ceil(num_padded_cols/72)]);

% Load data
load('data.mat')
% Extract features and labels
X = data(:, 1:end-1);
Y = data(:, end);
Y_str = cellstr(num2str(Y));
categories = unique(Y);
Y = categorical(Y_str, unique(Y_str));
[num_samples, num_features] = size(X);
num_padded_rows = ceil(num_samples/144)*144;
num_padded_cols = ceil(num_features/72)*72;
X_padded = [X, zeros(num_samples, num_padded_cols - num_features)];
X_reshaped = reshape(X_padded, [num_padded_rows/144, 8, 3, 3, ceil(num_padded_cols/72)]);
% Define CNN layers
layers = [    imageInputLayer([8, 3, 3, 2])
    convolution2dLayer(3,16,'Padding','same')
    batchNormalizationLayer
    reluLayer
    maxPooling2dLayer(2,'Stride',2)
    convolution2dLayer(3,32,'Padding','same')
    batchNormalizationLayer
    reluLayer
    maxPooling2dLayer(2,'Stride',2)
    convolution2dLayer(3,64,'Padding','same')
    batchNormalizationLayer
    reluLayer
    fullyConnectedLayer(length(categories))
    softmaxLayer
    classificationLayer];
% Define training options
options = trainingOptions('adam', ...
    'InitialLearnRate',1e-4, ...
    'MaxEpochs',20, ...
    'MiniBatchSize',32, ...
    'Shuffle','every-epoch', ...
    'Verbose',false, ...
    'Plots','training-progress');
% Train the CNN
net = trainNetwork(X_reshaped, Y, layers, options);

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

Govind KM 2024-9-24，10:16

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1958264-i-have-data-mat-file-and-i-am-working-on-load-forecasting-for-solar-power-with-cnn-i-am-facing-issu#answer_1521750

在 MATLAB Online 中打开

Hi @muhammad,

The reshape function requires the total number of elements in the input array to be preserved in the output array. Hence, the product of the specified dimensions must equal the total number of elements in the input.

In the provided code:

X = rand(4348,23); %Sample data with same size
[num_samples, num_features] = size(X);
num_padded_rows = ceil(num_samples/144)*144;
num_padded_cols = ceil(num_features/72)*72;
X_padded = [X, zeros(num_samples, num_padded_cols - num_features)];
numel(X_padded)
ans = 313056
%X_reshaped = reshape(X_padded, [num_padded_rows/144, 8, 3, 3, ceil(num_padded_cols/72)]);
prod([num_padded_rows/144, 8, 3, 3, ceil(num_padded_cols/72)])
ans = 2232

The total number of elements are unequal, leading to an error.

One way to resolve this is to pass "[]" as the first dimension to the reshape function, maintaining the remaining dimensions as [8,3,3,2] for the CNN layer. This lets the function calculate the necessary size automatically, ensuring the element count remains unchanged.

X_reshaped = reshape(X_padded, [], 8, 3, 3, 2);
size(X_reshaped)
ans = 1×5
        2174           8           3           3           2
<mw-icon class=""></mw-icon>
<mw-icon class=""></mw-icon>