Convolutional network with no image input

Hello

I'm tryng to build convolutional neural network with 2 wave input data (201 elements each).

However when I launch 'trainNetwork' with the input, I got this error message.

%%%%%%%%%%%%%%%%%%%%%%

Error using trainNetwork (line 170)

Invalid training data. X must be a 4-D array of images, an ImageDatastore, or a table.

%%%%%%%%%%%%%%%%%%%%%%

I looked for some solution but I got no infomation, furthermore some people say it is not possible to apply multiple inputs (2 or 4) to CNN.

I need some help.

Layers property

-----------------------------------------------------------------------------

1 'input' Image Input 1x201x2 images with 'zerocenter' normalization

2 'conv_1' Convolution 16 1x3 convolutions with stride [1 1] and padding 'same'

3 'BN_1' Batch Normalization Batch normalization

4 'relu_1' ReLU ReLU

5 'MaxPooling_1' Max Pooling 1x2 max pooling with stride [1 2] and padding [0 0 0 0]

6 'conv_2' Convolution 16 1x3 convolutions with stride [1 1] and padding 'same'

7 'BN_2' Batch Normalization Batch normalization

8 'relu_2' ReLU ReLU

9 'MaxPooling_2' Max Pooling 1x2 max pooling with stride [1 2] and padding [0 0 0 0]

10 'conv_3' Convolution 16 1x3 convolutions with stride [1 1] and padding 'same'

11 'BN_3' Batch Normalization Batch normalization

12 'relu_3' ReLU ReLU

13 'MaxPooling_3' Max Pooling 1x2 max pooling with stride [1 2] and padding [0 0 0 0]

14 'conv_4' Convolution 16 1x3 convolutions with stride [1 1] and padding 'same'

15 'BN_4' Batch Normalization Batch normalization

16 'relu_4' ReLU ReLU

17 'MaxPooling_4' Max Pooling 1x2 max pooling with stride [1 2] and padding [0 0 0 0]

18 'dropout' Dropout 20% dropout

19 'fullyConnect' Fully Connected 3 fully connected layer

20 'regressionOutput' Regression Output mean-squared-error

------------------------------------------------------------------------------------------------