Bayesian Deep Learning with monte carlo dropout Pytorch

[MERAH_Samia]

Am working on this
What do you think any advice/opinon ? please

Calculate Entropy for each class to measure uncertainty

I am trying to calculate Entropy per class for an image classification task to measure uncertainty on pytorch,using the MC Dropout method and the solution proposed in this link Measuring uncertainty using MC Dropout First,I have calculated the mean of each class per batch across different forward passes (class_mean_batch) and then for all the testloader (classes_mean) and then did some transformations to get (total_mean) to use it for calculating Entropy as shown in the code below def mcdrop…