How can I train CNN model with a dataset, whos image have mulitiple features

1 My data set is like the above image, each image has multi -features, All the image has the same size in height and width 1300x290

2I use image labeler to label the feature ,and got the dataset, as following.

3 I use a typical layer to train the CNN, as following.

4

Then I try the model

detector = trainFasterRCNNObjectDetector(trainingData, layers, options, ...

'NegativeOverlapRange', [0 0.3], ...

'PositiveOverlapRange', [0.6 1], ...

'NumRegionsToSample', [256 128 256 128], ...

'BoxPyramidScale', 1.2);

5 but failed, many erros happens.

６My quesiton is how to train a CNN model with the dataset ,where one image has several features?