Slower
num_gt_lesions = len(torch.unique(gt_label_cc)[torch.unique(gt_label_cc) != 0])

I have this snippet from here:

I have a model that uses dropout for MC prediction. It works fine in Python on my desktop. I’d like to execute the same algorithm on mobile platforms but the dropout does not seem to be applied. I get the same result each MC iteration when evaluating the model on mobile.

I am new to PyTorch so my question could be trivial.

I have a simple convolutional network for mnist data classification in pytorch. I followed up everything in a tutorial that I was watching except the batch size. In tutorial batch_size=100 and I chose batch_size=64
The answers were completely different after training: