Matlab neural network. Problem with RGB.

Hi all.

Recently began to study neural networks in Matlab. Did to guide semantic segmentation via model VGG-16. Downloaded the camvid dataset. Produced resize from 720х960 to 360х480. After that, the initial piece of code.

imgDir = fullfile('C:\Users\ras19\AppData\Local\Temp\CamVid\images\701_StillsRaw_full\image\imagesResized');
imds = imageDatastore(imgDir);
I = readimage(imds,1);
I = histeq(I);

classes = [
    "Sky"
    "Road"
    "RoadSide"
    "Car"
    "SideWalk"
    "Signs"
    "Post"
    "Buildings"
    "Backgrounds"
    "fence"
    "Person"
    ];
%Создание базы данных меток
labelIDs = camvidPixelLabelIDs();
% labelDir = fullfile('C:\Users\ras19\Desktop\Учёбка\ВКР\MY\Matlab\Test\PixelLabelData_7');
labelDir = fullfile('C:\Users\ras19\AppData\Local\Temp\CamVid\labels\label\labelsResized');
pxds = pixelLabelDatastore(labelDir,classes,labelIDs);

C = readimage(pxds,1);
cmap = camvidColorMap;
B = labeloverlay(I,C,'ColorMap',cmap);
imshow(B)

Gives this error:

Error using matlab.io.datastore.PixelLabelDatastore.label2cat (line 1033)
Pixel label image has scalar pixel label IDs instead of RGB-triplet pixel label IDs.

Error in matlab.io.datastore.PixelLabelDatastore/label2categorical (line 937)
                    L = matlab.io.datastore.PixelLabelDatastore.label2cat(...

Error in matlab.io.datastore.PixelLabelDatastore/readimage (line 544)
                    C = this.label2categorical(C, info);

Error in gaid (line 28)
C = readimage(pxds,1);
 

I noticed that after resizing the labels instead of the steel color in different shades of grey can this problem?

Functions that were used:

function labelIDs = camvidPixelLabelIDs()
labelIDs = { ...
    
    % "Sky"
    [
    128 128 128; ... % "Sky"
    ]
    
     % Road
    [
    128 064 128; ... % "Road"
    128 000 192; ... % "LaneMkgsDriv"
    192 000 064; ... % "LaneMkgsNonDriv"
    ]
    
       % "RoadSide"
    [
     128 128 192; ... % "RoadShoulder"
     064 192 128; ... % "ParkingBlock
    ]
    
        % "Car"
    [
    064 000 128; ... % "Car"
    064 128 192; ... % "SUVPickupTruck"
    192 128 192; ... % "Truck_Bus"
    192 064 128; ... % "Train"
    128 064 064; ... % "OtherMoving"
    000 128 192; ... % "Bicyclist"
    192 000 192; ... % "MotorcycleScooter"
    ]
    
      % "Sidewalk"
    [
    000 000 192; ... % "Sidewalk" 
    ]
    
       % "Signs"
    [
    192 128 128; ... % "SignSymbol"
    128 128 064; ... % "Misc_Text"
    000 064 064; ... % "TrafficLight"
    ]
    
    % "Post"
    [
    192 192 128; ... % "Column_Pole"
    000 000 064; ... % "TrafficCone"
    ]
    
    % "Buildings" 
    [
    000 128 064; ... % "Bridge"
    128 000 000; ... % "Building"
    064 192 000; ... % "Wall"
%     064 000 064; ... % "Tunnel"
    192 000 128; ... % "Archway"
    ]
    

     
    % "Backgrounds"
    [
    128 128 000; ... % "Tree"
    192 192 000; ... % "VegetationMisc"
    ]
    
 
    
    % "fence"
    [
    064 064 128; ... % "Fence"
    064 000 064; ... % "Tunnel"
    ]
    

    % "Person"
    [
    064 064 000; ... % "Pedestrian"
    192 128 064; ... % "Child"
    064 000 192; ... % "CartLuggagePram"
    064 128 064; ... % "Animal"
    ]
    
%     % "Bicyclist"
%     [
%     000 128 192; ... % "Bicyclist"
%     192 000 192; ... % "MotorcycleScooter"
%     ]
    
    };
end
function pixelLabelColorbar(cmap, classNames)
% Add a colorbar to the current axis. The colorbar is formatted
% to display the class names with the color.

colormap(gca,cmap)

% Add colorbar to current figure.
c = colorbar('peer', gca);

% Use class names for tick marks.
c.TickLabels = classNames;
numClasses = size(cmap,1);

% Center tick labels.
c.Ticks = 1/(numClasses*2):1/numClasses:1;

% Remove tick mark.
c.TickLength = 0;
end
% Создание карты цветов для каждого класса

function cmap = camvidColorMap()
% Define the colormap used by CamVid dataset.

cmap = [
    0 114 189;  %Sky
    217 83 25;  %Road
    237 177 32;  %RoadSide
    126 47 142;  %Car
    119 172 48;  %SideWalk
    77 190 238;  %Signs
    162 20 47;  %Post
    255 0 0;  %Buildings
    0 255 0;  %Backgrounds
    255 26 185;  %fence
    255 211 0 %Person
    ];
% Normalize between [0 1].
cmap = cmap ./ 255;
end
function imds = resizeCamVidImages(imds, imageFolder)
% Resize images to [360 480].

if ~exist(imageFolder,'dir') 
    mkdir(imageFolder)
else
    imds = imageDatastore(imageFolder);
    return; % Skip if images already resized
end

reset(imds)
while hasdata(imds)
    % Read an image.
    [I,info] = read(imds);     
    
    % Resize image.
    I = imresize(I,[360 480]);    
    
    % Write to disk.
    [~, filename, ext] = fileparts(info.Filename);
    imwrite(I,[imageFolder filename ext])
end

imds = imageDatastore(imageFolder);
end
function pxds = resizeCamVidPixelLabels(pxds, labelFolder)
% Resize pixel label data to [360 480].

classes = pxds.ClassNames;
labelIDs = 1:numel(classes);
if ~exist(labelFolder,'dir')
    mkdir(labelFolder)
else
    pxds = pixelLabelDatastore(labelFolder,classes,labelIDs);
    return; % Skip if images already resized
end

reset(pxds)
while hasdata(pxds)
    % Read the pixel data.
    [C,info] = read(pxds);
    
    % Convert from categorical to uint8.
    L = uint8(C);
    
    % Resize the data. Use 'nearest' interpolation to
    % preserve label IDs.
    L = imresize(L,[360 480],'nearest');
    
    % Write the data to disk.
    [~, filename, ext] = fileparts(info.Filename);
    imwrite(L,[labelFolder filename ext])
end

labelIDs = 1:numel(classes);
pxds = pixelLabelDatastore(labelFolder,classes,labelIDs);
end

[Kirill Karpov]

if you do not make a resize, then everything works.