deep-learning-v2-pytorch icon indicating copy to clipboard operation
deep-learning-v2-pytorch copied to clipboard

Published 20 hours ago • verified publisher icon udacity

why there is difference for averaging validation loss and testloss

Open guth0b opened this issue 2 years ago • 1 comments

to get total average valid loss you divide by len(valid_loader) but for avaerage test loss you divide by len(test_loader.dataset). This does not seems correct. And also you are multiplying the loss with batch_size in test runs, but you dont do it for validation. Why?

guth0b avatar Jun 07 '23 18:06 guth0b