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 mcdropout_test(batch_size,n_classes,model,T):

    #set non-dropout layers to eval mode

    #set dropout layers to train mode
    softmax = nn.Softmax(dim=1)
    classes_mean = []
    for images,labels in testloader:
        images =
        labels =
        classes_mean_batch = []
        with torch.no_grad():
          output_list = []
          #getting outputs for T forward passes
          for i in range(T):
            output = model(images)
            output = softmax(output)
            output_list.append(torch.unsqueeze(output, 0))
        concat_output =,0)
        # getting mean of each class per batch across multiple MCD forward passes
        for i in range (n_classes):
          mean = torch.mean(concat_output[:, : , i])
        # getting mean of each class for the testloader

    total_mean = []
    concat_classes_mean = torch.stack(classes_mean)

    for i in range (n_classes):
      concat_classes = concat_classes_mean[: , i]

    total_mean = torch.stack(total_mean)
    total_mean = np.asarray(total_mean.cpu())
    epsilon = sys.float_info.min
    # Calculating entropy across multiple MCD forward passes 
    entropy = (- np.sum(total_mean*np.log(total_mean + epsilon), axis=-1)).tolist()
    entropy = [i*(1/T) for i in entropy]
    for i in range(n_classes):
      print(f'entropy of class {i+1} is {entropy[i]:.4f}')

Can anyone please correct or confirm the implementation i have used to calculate Entropy of each class.