MATLAB: Option training progress plot for RCNN Detector

option training progress plot for rcnn detector

Hi Guys

I am looking if threre is anyway for getting the plot of training progress for RCNN Detector

I have checked Matlab and as per the link below but it does not support the plot training progress for RCNN

Note

trainRCNNObjectDetector does not support these training options:

The Plots value: 'training-progress'
The ValidationData, ValidationFrequency, or ValidationPatience options
The OutputFcn option.

https://www.mathworks.com/help/vision/ref/trainrcnnobjectdetector.html

Thanks

Best Answer

Hi,

The specific ‘training-progress’ is not available for ‘Plots’ Property for trainRCNNObjectDetector. I would suggest you to save the info that contains the information about training loss and accuracy after each iteration by using

[detector,info] = trainRCNNObjectDetector(___)

This info object will return Training Loss, Training Accuracy and Learning Rate for each epoch in a structure which you may access later for plotting the result for visualization. Dynamically visualizing the training progress on a plot is not supported. By this way you can see the training progress after the training finishes.

For Other factors in RCNN Detector Training please take a look at the Training Options.

Related Solutions

MATLAB: Monitor Deep Learning Training Progress

I tried reproducing the above issue using an example provided in the documentation -

digitDatasetPath = fullfile(matlabroot,'toolbox','nnet','nndemos','nndatasets','DigitDataset');
imds = imageDatastore(digitDatasetPath, 'IncludeSubfolders',true,'LabelSource','foldernames');
numTrainFiles = 750;
[imdsTrain,imdsValidation] = splitEachLabel(imds,numTrainFiles,'randomize');
inputSize = [28 28 1];
numClasses = 10;
layers = [
    imageInputLayer(inputSize)
    convolution2dLayer(5,20)
    batchNormalizationLayer
    reluLayer
    fullyConnectedLayer(numClasses)
    softmaxLayer
    classificationLayer];
options = trainingOptions('sgdm', ...
    'MaxEpochs',4, ...
    'ValidationData',imdsValidation, ...
    'ValidationFrequency',30, ...
    'Verbose',false, ...
    'Plots','training-progress');
net = trainNetwork(imdsTrain,layers,options);

I was able to view the training progress

Please crosscheck the spellings of Name Value pairs in trainingOptions

MATLAB: Manually Plotting the graph from R-CNN training parameters

Hi,

The trainingOptions for trainRCNNObjectDetector does not support plotting the train-progress while the training is going on, but the training parameters are returned at the end of training if trainRCNNObjectDetector is used with following arguments.

[detector,info] = trainRCNNObjectDetector(___)

In the script from the question following command looks incorrect,

[detector,info] = trainRCNNObjectDetector('Epoch','Mini-batch Loss','Training Accuracy','Base Learning Rate','Mini-batch Accuracy');

instead the above can be replaced by

[detector,info] = trainRCNNObjectDetector(trainingData, layers, options, 'NegativeOverlapRange', [0 0.3]);

Here info will be returned as a structure which contains the ‘Training Accuracy’, ‘Training Loss’ and ‘Base Learning Rate’ for each iteration. These can be then plotted as per required. The error was there because correct input arguments weren’t passed.

Best Answer

Related Solutions

MATLAB: Monitor Deep Learning Training Progress

MATLAB: Manually Plotting the graph from R-CNN training parameters

Related Question