GPU arrays support only fundamental numeric or logical data types

Question

Ricky Hartono 2021-1-15

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/717860-gpu-arrays-support-only-fundamental-numeric-or-logical-data-types

评论： Joss Knight 2021-1-23

I tried to use Faster R-CNN with the pretrained model of ResNet18 where I froze some of the layers to detect 5 different objects inside image. I've successfully train the model using only the training data (in table). However when I include the validation data, the MATLAB asked me to change the validation and training data to be in datastore format (basically I followed the steps here https://www.mathworks.com/help/vision/ug/object-detection-using-faster-r-cnn-deep-learning.html). I've tried to train the model, the training can go on, but there is a pop-up warning for every iteration(?) saying the GPU arrays support only fundamental numeric or logical data types. Also, the training plot for loss function can't be shown.

load data.mat
lgraph=resnet18_12_freeze
%trainingData
imds = imageDatastore(trainingData.imageFilename);
blds = boxLabelDatastore(trainingData(:,2:end));
trainingData=combine(imds,blds);
%validationData
imds = imageDatastore(validationData.imageFilename);
blds = boxLabelDatastore(validationData(:,2:end));
validationData=combine(imds,blds);
inputSize = [224 224 3];
trainingData = transform(trainingData, @(data)preprocessData(data,inputSize));
augmentedTrainingData = transform(trainingData,@augmentData);
augmentedData = cell(4,1);
trainingData = transform(augmentedTrainingData,@(data)preprocessData(data,inputSize));
validationData = transform(validationData,@(data)preprocessData(data,inputSize));
options = trainingOptions('sgdm', ...
'MiniBatchSize', 2, ...
'InitialLearnRate', 1e-3, ...
'MaxEpochs', 50, ...
'VerboseFrequency', 50, ...
'ValidationData', validationData, ...
'ValidationFrequency',50, ...
'ExecutionEnvironment', 'gpu', ...
'CheckpointPath', tempdir, ...
'Plots','training-progress');
  
  
      
detector = trainFasterRCNNObjectDetector(trainingData, lgraph, options, ...
        'NegativeOverlapRange',[0.1 0.5], ...
        'PositiveOverlapRange',[0.5 1]);

Warning message

Warning: GPU arrays support only fundamental numeric or logical data types. 
> In nnet.internal.cnn.util/TrainingPlotReporter/cleanUpAfterPlotError (line 109)
In nnet.internal.cnn.util/TrainingPlotReporter/reportIteration (line 58)
In nnet.internal.cnn.util/VectorReporter/computeAndReport (line 64)
In nnet.internal.cnn.util/VectorReporter/reportIteration (line 20)
In nnet.internal.cnn/Trainer/train (line 142)
In vision.internal.cnn.trainNetwork (line 102)
In trainFasterRCNNObjectDetector>iTrainEndToEnd (line 901)
In trainFasterRCNNObjectDetector (line 428)
In trainFasterRCNN (line 35) 

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

Joss Knight 2021-1-16

1
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/717860-gpu-arrays-support-only-fundamental-numeric-or-logical-data-types#answer_599225

It looks distinctly like one of your custom functions, preprocessData or augmentData, is doing something illegal with gpuArray objects. Try calling dbstop if all error so that MATLAB will break at the problematic line of code.

4 个评论
显示 2更早的评论隐藏 2更早的评论

Ricky Hartono 2021-1-21

Ok, thank you for the answer

Joss Knight 2021-1-23

在 MATLAB Online 中打开

Here's an idea: wrap the code in your custom functions preprocessData and augmentData with a try...catch block. Then you can put a breakpoint inside the catch clause, allowing you to determine the original source of the error - assuming it was indeed your custom code.

try
    % Put your original code here
catch ME
    % Put a breakpoint here so you can inspect the error
    getReport(ME) % This displays the error and call stack
    rethrow(ME);
end