deep_kaur asked . 2021-07-14

How to plot training loss for Covolutional Neural Nets?

 function plotTrainingLoss(info)
 persistent plotObj

 info.State == "start"
    plotObj = animatedline('Color','r');
    xlabel("Iteration")
    ylabel("Loss")
    title("Training loss evolution")

 elseif info.State == "iteration"

    addpoints(plotObj,info.Iteration,info.TrainingLoss)
    drawnow limitrate nocallbacks

    fprintf('%d \n',info.TrainingLoss)
       end
    end

    Initializing image normalization.
|=========================================================================================|
|     Epoch    |   Iteration  | Time Elapsed |  Mini-batch  |  Mini-batch  | Base Learning|
|              |              |  (seconds)   |     Loss     |   Accuracy   |     Rate     |
|=========================================================================================|
|            1 |            1 |         0.33 |       2.0795 |       14.84% |       0.0010 |
Error using trainNetwork (line 133)
Invalid type for argument Y. Type should be double.

 Error in TrainOwnCNN_Advanced (line 108) 
 CNN = trainNetwork(trainingData,layers,options);

    Initializing image normalization.
|=========================================================================================|
|     Epoch    |   Iteration  | Time Elapsed |  Mini-batch  |  Mini-batch  | Base Learning|
|              |              |  (seconds)   |     Loss     |   Accuracy   |     Rate     |
|=========================================================================================|
|            1 |            1 |         0.23 |       2.0832 |        7.81% |       0.0010 |
2.083199e+00 
2.083350e+00 
2.082194e+00 
2.081159e+00 
2.080728e+00 
2.080156e+00 
2.079782e+00 
2.080018e+00 
2.077905e+00 
2.078161e+00 
2.078137e+00

traininfo , loss function , convolution neural... , cnn , info.trainingloss , train cnn