rcnn mini batch accuracy

Hey, Im trying to train a rcnn to recognize a nose in a thermal picture.

during the training I get 'mini batch accuracy' 100%. my qustion is how is this vaule is calculted?

when I tried to use my rcnn on my own training data it showed very bed results. (most picture are not beining assigned any labeling box).

Answer 1

[Xiangxue Wang]

Hi,

I have met the same situation as you described above. I checked their codes for accuracy calculation, it looks like the accuracy definition is number of correctely detected boxes over the number of positive boxes within the training set.

specific function/class is called FasterRCNNEndToEndTrainingSummary

%%FasterRCNNEndToEndTrainingSummary
function [accuracy, numObservations] = iClassificationAccuracyMetric(Y,T)
[~, yIntegers] = max(Y, [], 3);
[t, tIntegers] = max(T, [], 3);
x = (t.* (yIntegers == tIntegers));
numObservations = nnz(T); 
if numObservations == 0
    % None of the proposals where marked as positive or negative sample
    % based on the positive/negative overlap ratios. In this case, the Fast
    % R-CNN sub-network does nothing during training and we should report
    % [] accuracy.
    accuracy = [];
else
    accuracy = gather( 100 * (sum(x(:)) / numObservations) );
end
end

For very bad results you mentioned as no assigment of box in test set, I would suggest to lower the threshold when using the detect function to see if any activations in cnn for RPN to be identified. But, based on what you described, I would assume the training doesn't learn much to differentiate the nose from the background. You may think about tweaking your training data somehow during preprocessing.