Layer 'conv1': Invalid input data. Undefined function 'changeStorage' for input arguments of type 'deep.inte​rnal.forma​t.DataLayo​ut'.

I implement Object Detection Using YOLO v3 Deep Learning and I get the following error.

Same error in my own dataset and standard(vehicleDatasetImages) dataset.

II am following the operations on this link.

line : [gradients, state, lossInfo] = dlfeval(@modelGradients, yolov3Detector, XTrain, YTrain, penaltyThreshold);

Error: Layer 'conv1': Invalid input data. Undefined function 'changeStorage' for input arguments of type 'deep.internal.format.DataLayout'.

Please help me?

Matlab version is 2021a :(

Answer 1

[Shraddha Jain]

Hi Kursat,

Make sure that you have added all the Supporting Functions mentioned in the example Object Detection Using YOLO v3 Deep Learning. Refering to the code that you have specified above, it is possible that the supporting function modelGradients is missing in your script.

Use the below MATLAB command to open the live script of the mentioned example from Command Window:

openExample('deeplearning_shared/ObjectDetectionUsingYOLOV3DeepLearningExample') 

Hope this helps!